deepseek-r1-distill-llama-8b
This page lists all pretrained SAEs available for deepseek-r1-distill-llama-8b.
deepseek-r1-distill-llama-8b-qresearch
- Huggingface Repo: qresearch/DeepSeek-R1-Distill-Llama-8B-SAE-l19
| id | neuronpedia | hook_name | d_sae | normalize_activations |
|---|---|---|---|---|
blocks.19.hook_resid_post Load this SAE |
deepseek-r1-distill-llama-8b/19-qresearch-res-65k | blocks.19.hook_resid_post | 65536 | none |
llama_scope_r1_distill
- Huggingface Repo: fnlp/Llama-Scope-R1-Distill
| id | neuronpedia | hook_name | d_sae | normalize_activations |
|---|---|---|---|---|
l0r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/0-llamascope-slimpj-res-32k | blocks.0.hook_resid_post | 32768 | expected_average_only_in |
l1r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/1-llamascope-slimpj-res-32k | blocks.1.hook_resid_post | 32768 | expected_average_only_in |
l2r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/2-llamascope-slimpj-res-32k | blocks.2.hook_resid_post | 32768 | expected_average_only_in |
l3r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/3-llamascope-slimpj-res-32k | blocks.3.hook_resid_post | 32768 | expected_average_only_in |
l4r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/4-llamascope-slimpj-res-32k | blocks.4.hook_resid_post | 32768 | expected_average_only_in |
l5r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/5-llamascope-slimpj-res-32k | blocks.5.hook_resid_post | 32768 | expected_average_only_in |
l6r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/6-llamascope-slimpj-res-32k | blocks.6.hook_resid_post | 32768 | expected_average_only_in |
l7r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/7-llamascope-slimpj-res-32k | blocks.7.hook_resid_post | 32768 | expected_average_only_in |
l8r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/8-llamascope-slimpj-res-32k | blocks.8.hook_resid_post | 32768 | expected_average_only_in |
l9r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/9-llamascope-slimpj-res-32k | blocks.9.hook_resid_post | 32768 | expected_average_only_in |
l10r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/10-llamascope-slimpj-res-32k | blocks.10.hook_resid_post | 32768 | expected_average_only_in |
l11r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/11-llamascope-slimpj-res-32k | blocks.11.hook_resid_post | 32768 | expected_average_only_in |
l12r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/12-llamascope-slimpj-res-32k | blocks.12.hook_resid_post | 32768 | expected_average_only_in |
l13r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/13-llamascope-slimpj-res-32k | blocks.13.hook_resid_post | 32768 | expected_average_only_in |
l14r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/14-llamascope-slimpj-res-32k | blocks.14.hook_resid_post | 32768 | expected_average_only_in |
l15r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/15-llamascope-slimpj-res-32k | blocks.15.hook_resid_post | 32768 | expected_average_only_in |
l16r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/16-llamascope-slimpj-res-32k | blocks.16.hook_resid_post | 32768 | expected_average_only_in |
l17r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/17-llamascope-slimpj-res-32k | blocks.17.hook_resid_post | 32768 | expected_average_only_in |
l18r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/18-llamascope-slimpj-res-32k | blocks.18.hook_resid_post | 32768 | expected_average_only_in |
l19r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/19-llamascope-slimpj-res-32k | blocks.19.hook_resid_post | 32768 | expected_average_only_in |
l20r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/20-llamascope-slimpj-res-32k | blocks.20.hook_resid_post | 32768 | expected_average_only_in |
l21r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/21-llamascope-slimpj-res-32k | blocks.21.hook_resid_post | 32768 | expected_average_only_in |
l22r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/22-llamascope-slimpj-res-32k | blocks.22.hook_resid_post | 32768 | expected_average_only_in |
l23r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/23-llamascope-slimpj-res-32k | blocks.23.hook_resid_post | 32768 | expected_average_only_in |
l24r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/24-llamascope-slimpj-res-32k | blocks.24.hook_resid_post | 32768 | expected_average_only_in |
l25r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/25-llamascope-slimpj-res-32k | blocks.25.hook_resid_post | 32768 | expected_average_only_in |
l26r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/26-llamascope-slimpj-res-32k | blocks.26.hook_resid_post | 32768 | expected_average_only_in |
l27r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/27-llamascope-slimpj-res-32k | blocks.27.hook_resid_post | 32768 | expected_average_only_in |
l28r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/28-llamascope-slimpj-res-32k | blocks.28.hook_resid_post | 32768 | expected_average_only_in |
l29r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/29-llamascope-slimpj-res-32k | blocks.29.hook_resid_post | 32768 | expected_average_only_in |
l30r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/30-llamascope-slimpj-res-32k | blocks.30.hook_resid_post | 32768 | expected_average_only_in |
l31r_800m_slimpajama Load this SAE |
deepseek-r1-distill-llama-8b/31-llamascope-slimpj-res-32k | blocks.31.hook_resid_post | 32768 | expected_average_only_in |
l0r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/0-llamascope-slimpj-openr1-res-32k | blocks.0.hook_resid_post | 32768 | expected_average_only_in |
l1r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/1-llamascope-slimpj-openr1-res-32k | blocks.1.hook_resid_post | 32768 | expected_average_only_in |
l2r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/2-llamascope-slimpj-openr1-res-32k | blocks.2.hook_resid_post | 32768 | expected_average_only_in |
l3r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/3-llamascope-slimpj-openr1-res-32k | blocks.3.hook_resid_post | 32768 | expected_average_only_in |
l4r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/4-llamascope-slimpj-openr1-res-32k | blocks.4.hook_resid_post | 32768 | expected_average_only_in |
l5r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/5-llamascope-slimpj-openr1-res-32k | blocks.5.hook_resid_post | 32768 | expected_average_only_in |
l6r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/6-llamascope-slimpj-openr1-res-32k | blocks.6.hook_resid_post | 32768 | expected_average_only_in |
l7r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/7-llamascope-slimpj-openr1-res-32k | blocks.7.hook_resid_post | 32768 | expected_average_only_in |
l8r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/8-llamascope-slimpj-openr1-res-32k | blocks.8.hook_resid_post | 32768 | expected_average_only_in |
l9r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/9-llamascope-slimpj-openr1-res-32k | blocks.9.hook_resid_post | 32768 | expected_average_only_in |
l10r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/10-llamascope-slimpj-openr1-res-32k | blocks.10.hook_resid_post | 32768 | expected_average_only_in |
l11r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/11-llamascope-slimpj-openr1-res-32k | blocks.11.hook_resid_post | 32768 | expected_average_only_in |
l12r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/12-llamascope-slimpj-openr1-res-32k | blocks.12.hook_resid_post | 32768 | expected_average_only_in |
l13r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/13-llamascope-slimpj-openr1-res-32k | blocks.13.hook_resid_post | 32768 | expected_average_only_in |
l14r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/14-llamascope-slimpj-openr1-res-32k | blocks.14.hook_resid_post | 32768 | expected_average_only_in |
l15r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/15-llamascope-slimpj-openr1-res-32k | blocks.15.hook_resid_post | 32768 | expected_average_only_in |
l16r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/16-llamascope-slimpj-openr1-res-32k | blocks.16.hook_resid_post | 32768 | expected_average_only_in |
l17r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/17-llamascope-slimpj-openr1-res-32k | blocks.17.hook_resid_post | 32768 | expected_average_only_in |
l18r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/18-llamascope-slimpj-openr1-res-32k | blocks.18.hook_resid_post | 32768 | expected_average_only_in |
l19r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/19-llamascope-slimpj-openr1-res-32k | blocks.19.hook_resid_post | 32768 | expected_average_only_in |
l20r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/20-llamascope-slimpj-openr1-res-32k | blocks.20.hook_resid_post | 32768 | expected_average_only_in |
l21r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/21-llamascope-slimpj-openr1-res-32k | blocks.21.hook_resid_post | 32768 | expected_average_only_in |
l22r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/22-llamascope-slimpj-openr1-res-32k | blocks.22.hook_resid_post | 32768 | expected_average_only_in |
l23r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/23-llamascope-slimpj-openr1-res-32k | blocks.23.hook_resid_post | 32768 | expected_average_only_in |
l24r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/24-llamascope-slimpj-openr1-res-32k | blocks.24.hook_resid_post | 32768 | expected_average_only_in |
l25r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/25-llamascope-slimpj-openr1-res-32k | blocks.25.hook_resid_post | 32768 | expected_average_only_in |
l26r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/26-llamascope-slimpj-openr1-res-32k | blocks.26.hook_resid_post | 32768 | expected_average_only_in |
l27r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/27-llamascope-slimpj-openr1-res-32k | blocks.27.hook_resid_post | 32768 | expected_average_only_in |
l28r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/28-llamascope-slimpj-openr1-res-32k | blocks.28.hook_resid_post | 32768 | expected_average_only_in |
l29r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/29-llamascope-slimpj-openr1-res-32k | blocks.29.hook_resid_post | 32768 | expected_average_only_in |
l30r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/30-llamascope-slimpj-openr1-res-32k | blocks.30.hook_resid_post | 32768 | expected_average_only_in |
l31r_400m_slimpajama_400m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/31-llamascope-slimpj-openr1-res-32k | blocks.31.hook_resid_post | 32768 | expected_average_only_in |
l0r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/0-llamascope-openr1-res-32k | blocks.0.hook_resid_post | 32768 | expected_average_only_in |
l1r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/1-llamascope-openr1-res-32k | blocks.1.hook_resid_post | 32768 | expected_average_only_in |
l2r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/2-llamascope-openr1-res-32k | blocks.2.hook_resid_post | 32768 | expected_average_only_in |
l3r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/3-llamascope-openr1-res-32k | blocks.3.hook_resid_post | 32768 | expected_average_only_in |
l4r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/4-llamascope-openr1-res-32k | blocks.4.hook_resid_post | 32768 | expected_average_only_in |
l5r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/5-llamascope-openr1-res-32k | blocks.5.hook_resid_post | 32768 | expected_average_only_in |
l6r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/6-llamascope-openr1-res-32k | blocks.6.hook_resid_post | 32768 | expected_average_only_in |
l7r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/7-llamascope-openr1-res-32k | blocks.7.hook_resid_post | 32768 | expected_average_only_in |
l8r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/8-llamascope-openr1-res-32k | blocks.8.hook_resid_post | 32768 | expected_average_only_in |
l9r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/9-llamascope-openr1-res-32k | blocks.9.hook_resid_post | 32768 | expected_average_only_in |
l10r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/10-llamascope-openr1-res-32k | blocks.10.hook_resid_post | 32768 | expected_average_only_in |
l11r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/11-llamascope-openr1-res-32k | blocks.11.hook_resid_post | 32768 | expected_average_only_in |
l12r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/12-llamascope-openr1-res-32k | blocks.12.hook_resid_post | 32768 | expected_average_only_in |
l13r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/13-llamascope-openr1-res-32k | blocks.13.hook_resid_post | 32768 | expected_average_only_in |
l14r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/14-llamascope-openr1-res-32k | blocks.14.hook_resid_post | 32768 | expected_average_only_in |
l15r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/15-llamascope-openr1-res-32k | blocks.15.hook_resid_post | 32768 | expected_average_only_in |
l16r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/16-llamascope-openr1-res-32k | blocks.16.hook_resid_post | 32768 | expected_average_only_in |
l17r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/17-llamascope-openr1-res-32k | blocks.17.hook_resid_post | 32768 | expected_average_only_in |
l18r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/18-llamascope-openr1-res-32k | blocks.18.hook_resid_post | 32768 | expected_average_only_in |
l19r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/19-llamascope-openr1-res-32k | blocks.19.hook_resid_post | 32768 | expected_average_only_in |
l20r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/20-llamascope-openr1-res-32k | blocks.20.hook_resid_post | 32768 | expected_average_only_in |
l21r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/21-llamascope-openr1-res-32k | blocks.21.hook_resid_post | 32768 | expected_average_only_in |
l22r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/22-llamascope-openr1-res-32k | blocks.22.hook_resid_post | 32768 | expected_average_only_in |
l23r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/23-llamascope-openr1-res-32k | blocks.23.hook_resid_post | 32768 | expected_average_only_in |
l24r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/24-llamascope-openr1-res-32k | blocks.24.hook_resid_post | 32768 | expected_average_only_in |
l25r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/25-llamascope-openr1-res-32k | blocks.25.hook_resid_post | 32768 | expected_average_only_in |
l26r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/26-llamascope-openr1-res-32k | blocks.26.hook_resid_post | 32768 | expected_average_only_in |
l27r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/27-llamascope-openr1-res-32k | blocks.27.hook_resid_post | 32768 | expected_average_only_in |
l28r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/28-llamascope-openr1-res-32k | blocks.28.hook_resid_post | 32768 | expected_average_only_in |
l29r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/29-llamascope-openr1-res-32k | blocks.29.hook_resid_post | 32768 | expected_average_only_in |
l30r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/30-llamascope-openr1-res-32k | blocks.30.hook_resid_post | 32768 | expected_average_only_in |
l31r_800m_openr1_math Load this SAE |
deepseek-r1-distill-llama-8b/31-llamascope-openr1-res-32k | blocks.31.hook_resid_post | 32768 | expected_average_only_in |
×