Instructions to use suchitg/llama_scope_lxa_8xq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use suchitg/llama_scope_lxa_8xq with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
|
Download README.md from suchitg/llama_scope_lxa_8xq: direct link, hf CLI and curl.
- Browser
- Download file 296 Bytes
-
https://huggingface.co/suchitg/llama_scope_lxa_8xq/resolve/main/README.md
- Command line
-
hf download hf://suchitg/llama_scope_lxa_8xq/README.md
-
curl -L -o README.md https://huggingface.co/suchitg/llama_scope_lxa_8xq/resolve/main/README.md
296 Bytes
metadata
library_name: saelens
SAEs for use with the SAELens library
This repository contains the following SAEs:
- l12a_8x
Load these SAEs using SAELens as below:
from sae_lens import SAE
sae, cfg_dict, sparsity = SAE.from_pretrained("suchitg/llama_scope_lxa_8xq", "<sae_id>")