Downloads · 30 days
0
sae-deepseek-r1-llama-8b
andreuka18/sae-deepseek-r1-llama-8b
sae-deepseek-r1-llama-8b is a machine learning model from andreuka18. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for saelens.
This repository contains the following SAEs: - model.layers.19
Access
Public
Updated Apr 26, 2025
Repo size
25.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors25.8 GB · 100%
At a glance
- Library
- saelens
- Access
- Public
- Created
- Apr 8, 2025
- Updated
- Apr 26, 2025
- SHA
- 0927600e
Model card
From the Hugging Face model README
SAEs for use with the SAELens library
This repository contains the following SAEs:
- model.layers.19
Load these SAEs using SAELens as below:
from sae_lens import SAE
sae, cfg_dict, sparsity = SAE.from_pretrained("andreuka18/sae-deepseek-r1-llama-8b", "<sae_id>")
- Library
- saelens
- Created
- Apr 8, 2025
- Updated
- Apr 26, 2025