PaulPauls/llama3_interpretability_sae
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Language:Python
Total stars: 364
Stars trend:
22 Nov 2024
12am ██▊ +22
1am ███▌ +28
2am ██▋ +21
3am ██▏ +17
4am ██ +16
5am ██▋ +21
6am █▋ +13
7am █▉ +15
8am ██▏ +17
9am █▍ +11
10am █▎ +10
11am █▎ +10
#python
#featureextraction, #featuresteering, #llama3, #llminterpretability, #openresearch, #pytorch, #sparseautoencoder