llama3_interpretability_sae icon indicating copy to clipboard operation
llama3_interpretability_sae copied to clipboard

Published 8 months ago • verified publisher icon PaulPauls
→

Metadata

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

← Metadata

624
Stars
36
Forks
624
Watchers

Owner

verified publisher icon PaulPauls

Metadata

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

Back