Hugging Face's logo
Activity Feed

AI & ML interests

Large language models, scaling laws, AI Alignment, democratization of DL

Recent Activity
davidoj01  published a dataset 2 days ago
EleutherAI/hack-ignition-benchmark
davidoj01  updated a dataset 2 days ago
EleutherAI/hack-ignition-benchmark
davidoj01  updated a model 4 days ago
EleutherAI/qwen3-8b-djinnsdf-dolci
View all activity

Papers

Agent Memory Is a Surface for Endogenous Authorization Laundering

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

View all Papers

Organization Card
Community About org cards

Welcome to EleutherAI's HuggingFace page. We are a non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence. Our open source models are hosted here on HuggingFace.

You may also be interested in our GitHub, website, or Discord server.

Collections 10

Data Attribution
Leave-1%-out retrain banks and datasets for training-data attribution: measured per-query loss changes, the ground truth for LDS.
Data Attribution
Leave-1%-out retrain banks and datasets for training-data attribution: measured per-query loss changes, the ground truth for LDS.
View 10 collections