PrototypeCommon
OpenMOSS/Llamascopium
A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods
- Owner
- OpenMOSS (organization)
- Stars
- Stars: 232
- Forks
- Forks: 31
- Language
- Python
- License
- None
- Created
- 2024
- Topics
- interpretabilitymechanistic-interpretabilitysparse-autoencoderssparse-dictionarycircuit-tracinglanguage-models
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by OpenMOSS
All 25 repos by OpenMOSS- OpenMOSS/MOSSStars: 12,328PythonStable
- OpenMOSS/MOSS-TTS-NanoStars: 4,596PythonRC
- OpenMOSS/MOSS-TTSStars: 4,280PythonRC
- OpenMOSS/MOSS-ImageStars: 2,456PythonRC
- OpenMOSS/MOSS-Transcribe-DiarizeStars: 2,244PythonRC
- OpenMOSS/Awesome-WAMStars: 1,510HTMLBeta
Nearby in Python
All Python repos- Frankweb33/flybrain-robot-bridgeStars: 232PythonPrototype
- 10291124jcjc-dotcom/ai-character-swapStars: 232PythonPrototype
- LYiHub/pub-street-fighter-aiStars: 232PythonPrototype
- mnot/nbhttpStars: 232PythonPrototype
- lucjon/Py-StackExchangeStars: 232PythonPrototype
- nanpy/nanpyStars: 232PythonPrototype