google-deepmind / dangerous-capability-evaluationsLinks
☆54Updated 8 months ago
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:
- ☆76Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆105Updated last year
- METR Task Standard☆147Updated 4 months ago
- ☆28Updated last year
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆60Updated this week
- ☆22Updated this week
- ☆131Updated 2 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆94Updated this week
- Collection of evals for Inspect AI☆144Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- Measuring the situational awareness of language models☆35Updated last year
- Redwood Research's transformer interpretability tools☆15Updated 3 years ago
- Sparse Autoencoder Training Library☆50Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated 11 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆76Updated last year
- ☆22Updated 7 months ago
- we got you bro☆35Updated 10 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆107Updated last year
- ☆132Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated last week
- ☆31Updated last year
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆42Updated last year
- Open source interpretability artefacts for R1.☆140Updated last month
- ☆62Updated last week
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆22Updated 3 months ago
- ☆96Updated 2 months ago
- Small, simple agent task environments for training and evaluation☆18Updated 7 months ago
- Attribution-based Parameter Decomposition☆23Updated this week