AlphaUncommon
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.
Archived: this repository is read-only
- Owner
- PaulPauls (personal account)
- Stars
- Stars: 641
- Forks
- Forks: 40
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- feature-extractionfeature-steeringllama3llm-interpretabilityopen-researchpytorchsparse-autoencoder
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by PaulPauls
All 2 repos by PaulPauls- PaulPauls/Tensorflow-NeuroevolutionStars: 127PythonPrototype
Nearby in Python
All Python repos- isaac-sim/IsaacLab-ArenaStars: 641PythonAlpha
- ChrisHayduk/minAlphaFold2Stars: 641PythonAlpha
- featherless-ai/simple-jevStars: 641PythonAlpha
- diefenbach/django-lfsStars: 641PythonAlpha
- pysmt/pysmtStars: 641PythonAlpha
- modflowpy/flopyStars: 641PythonAlpha