Downloads · 30 days
0
Llama-3.2-3B-sae
seonglae/Llama-3.2-3B-sae
Llama-3.2-3B-sae is a machine learning model from seonglae. 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: - Llama-3.2-3Bblocks.21.hookresidpre18432topk640.000149fineweb512 - Llama-3.2-3Bblocks.21.hookresidpre18432topk640.000149faithful-llama3.2-3b512 - Llama-3.2-3Bblocks.21.hoo…
Access
Public
Updated Jul 2, 2025
Repo size
906 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors906 MB · 100%
At a glance
- Library
- saelens
- Access
- Public
- Created
- Apr 8, 2025
- Updated
- Jul 2, 2025
- SHA
- 030551c3
Model card
From the Hugging Face model README
SAEs for use with the SAELens library
This repository contains the following SAEs:
- Llama-3.2-3B_blocks.21.hook_resid_pre_18432_topk_64_0.0001_49_fineweb_512
- Llama-3.2-3B_blocks.21.hook_resid_pre_18432_topk_64_0.0001_49_faithful-llama3.2-3b_512
- Llama-3.2-3B_blocks.21.hook_resid_pre_18432_topk_64_0.0001_42_fineweb_512
- Llama-3.2-3B_blocks.21.hook_resid_pre_18432_topk_64_0.0001_42_faithful-llama3.2-3b_512
Load these SAEs using SAELens as below:
from sae_lens import SAE
sae, cfg_dict, sparsity = SAE.from_pretrained("seonglae/Llama-3.2-3B-sae", "<sae_id>")
Citation
@inproceedings{cho2025faithfulsae,
title={Faithful{SAE}: Towards Capturing Faithful Features with Sparse Autoencoders
without External Datasets Dependency},
author={Seonglae Cho and Harryn Oh and Donghyun Lee and Luis Eduardo Rodrigues Vieira
and Andrew Bermingham and Ziad El Sayed},
booktitle={ACL 2025 Student Research Workshop},
year={2025},
url={https://openreview.net/forum?id=tBn9ChHGG9}
}
- Library
- saelens
- Created
- Apr 8, 2025
- Updated
- Jul 2, 2025