Downloads · 30 days
104
100% of all-time downloads
andreuka18/deepseek-r1-distill-llama-8b-lmsys-openthoughts
deepseek-r1-distill-llama-8b-lmsys-openthoughts is a text generation model from andreuka18. Use it when you need the model to write or continue text. It is set up for saelens. The card lists the license as mit.
This repository contains the following SAEs: - blocks.19.hookresidpost
Downloads · 30 days
104
100% of all-time downloads
All-time downloads
104
Public
Repo size
4.3 GB
Likes
1
Public
Click a slice to open those files.
.safetensors2.1 GB · 100%
From the Hugging Face model README
This repository contains the following SAEs:
Model described in the paper I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders. Code available at https://github.com/AIRI-Institute/SAE-Reasoning
Load these SAEs using SAELens as below:
from sae_lens import SAE
sae, cfg_dict, sparsity = SAE.from_pretrained("andreuka18/deepseek-r1-distill-llama-8b-lmsys-openthoughts", "<sae_id>")