Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
andreuka18
/
deepseek-r1-distill-llama-8b-lmsys-openthoughts
like
0
Text Generation
SAELens
arxiv:
2503.18878
License:
mit
Model card
Files
Files and versions
Community
1
Use this model
refs/pr/1
deepseek-r1-distill-llama-8b-lmsys-openthoughts
/
blocks.19.hook_resid_post
2 contributors
History:
4 commits
andreuka18
Update blocks.19.hook_resid_post/cfg.json
73fb311
verified
24 days ago
cfg.json
2.54 kB
Update blocks.19.hook_resid_post/cfg.json
24 days ago
sae_weights.safetensors
2.15 GB
LFS
Upload SAE blocks.19.hook_resid_post
24 days ago
sparsity.safetensors
262 kB
LFS
Upload SAE blocks.19.hook_resid_post
24 days ago