METR / task-standard
METR Task Standard
☆143Updated last month
Alternatives and similar repositories for task-standard:
Users that are interested in task-standard are comparing it to the libraries listed below
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆80Updated this week
- ☆84Updated this week
- Mechanistic Interpretability Visualizations using React☆233Updated 2 months ago
- ☆52Updated 5 months ago
- ☆60Updated last month
- ☆15Updated 2 weeks ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆206Updated last year
- ☆29Updated 10 months ago
- (Model-written) LLM evals library☆18Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆184Updated 2 months ago
- ☆123Updated last month
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆115Updated 2 years ago
- ☆210Updated 5 months ago
- Machine Learning for Alignment Bootcamp☆71Updated 2 years ago
- ☆10Updated 8 months ago
- Draw more samples☆186Updated 8 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆162Updated 4 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆93Updated last year
- Tools for studying developmental interpretability in neural networks.☆86Updated last month
- Collection of evals for Inspect AI☆87Updated this week
- ☆120Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 2 years ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆15Updated 3 months ago
- ☆60Updated 3 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆197Updated this week
- ☆258Updated 8 months ago
- ☆26Updated 11 months ago