google-deepmind / dangerous-capability-evaluationsLinks
☆58Updated last week
Alternatives and similar repositories for dangerous-capability-evaluations
Users that are interested in dangerous-capability-evaluations are comparing it to the libraries listed below
Sorting:
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆118Updated last year
- ☆102Updated 5 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- ☆142Updated 3 weeks ago
- METR Task Standard☆162Updated 8 months ago
- ☆138Updated 2 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆93Updated last year
- Collection of evals for Inspect AI☆241Updated this week
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆111Updated this week
- ☆104Updated last week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆208Updated this week
- Open source interpretability artefacts for R1.☆160Updated 5 months ago
- Inference API for many LLMs and other useful tools for empirical research☆74Updated last week
- ☆53Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆99Updated this week
- ☆97Updated 2 months ago
- we got you bro☆36Updated last year
- ☆109Updated 7 months ago
- Open Source Replication of Anthropic's Alignment Faking Paper☆51Updated 6 months ago
- ☆29Updated last year
- ☆26Updated 11 months ago
- ☆216Updated 7 months ago
- ☆301Updated last year
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated this week
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- ☆136Updated this week