SII-OpenMOSS
OpenMOSS presents a collection of our research on LLMs, supported by SII, Fudan and Mosi.
Pinned Loading
Repositories
Showing 10 of 16 repositories
- Language-Model-SAEs Public
For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
OpenMOSS/Language-Model-SAEs’s past year of commit activity - UnifiedToolHub Public
UnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide training preparation, annotation, and evaluation functionalities.
OpenMOSS/UnifiedToolHub’s past year of commit activity - Thus-Spake-Long-Context-LLM Public
a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation
OpenMOSS/Thus-Spake-Long-Context-LLM’s past year of commit activity - ReAttention Public
[ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolation
OpenMOSS/ReAttention’s past year of commit activity - Ultra-Innerthought Public
Ultra-Innerthought is a bilingual (Chinese and English) open-domain R1/o1 style SFT dataset.
OpenMOSS/Ultra-Innerthought’s past year of commit activity - TransformerLens Public Forked from TransformerLensOrg/TransformerLens
A library for mechanistic interpretability of GPT-style language models
OpenMOSS/TransformerLens’s past year of commit activity - LongSafety Public
OpenMOSS/LongSafety’s past year of commit activity
