METR / vivariaLinks
Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
☆108Updated last week
Alternatives and similar repositories for vivaria
Users that are interested in vivaria are comparing it to the libraries listed below
Sorting:
- METR Task Standard☆158Updated 6 months ago
- ☆26Updated 2 months ago
- Collection of evals for Inspect AI☆209Updated last week
- Sphynx Hallucination Induction☆53Updated 6 months ago
- ☆101Updated 5 months ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆88Updated this week
- ☆117Updated 2 weeks ago
- ☆98Updated 4 months ago
- ☆139Updated last week
- Open source interpretability artefacts for R1.☆158Updated 4 months ago
- ☆195Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆197Updated 9 months ago
- Inference-time scaling for LLMs-as-a-judge.☆276Updated last month
- Red-Teaming Language Models with DSPy☆208Updated 6 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- ⚖️ Awesome LLM Judges ⚖️☆122Updated 3 months ago
- ☆56Updated 3 weeks ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- ☆130Updated 5 months ago
- explore token trajectory trees on instruct and base models☆133Updated 2 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆177Updated 5 months ago
- ☆217Updated 2 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆112Updated last year
- An attribution library for LLMs☆42Updated 11 months ago
- ☆29Updated last year
- ☆291Updated last year
- A framework for optimizing DSPy programs with RL☆150Updated this week
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆310Updated 2 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆95Updated 4 months ago
- ☆98Updated 2 weeks ago