MinhxLe / subliminal-learningLinks
☆108Updated this week
Alternatives and similar repositories for subliminal-learning
Users that are interested in subliminal-learning are comparing it to the libraries listed below
Sorting:
- ☆153Updated 5 months ago
- ☆65Updated last week
- Open source interpretability artefacts for R1.☆170Updated 9 months ago
- Public repository containing METR's DVC pipeline for eval data analysis☆199Updated last week
- ☆118Updated 3 weeks ago
- ☆133Updated 3 months ago
- Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"☆88Updated 11 months ago
- ☆58Updated 2 years ago
- ☆36Updated last year
- ☆93Updated last month
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆127Updated last year
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Open Source Replication of Anthropic's Alignment Faking Paper☆54Updated 10 months ago
- An attribution library for LLMs☆46Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆135Updated 3 years ago
- ☆33Updated 8 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Updated 2 weeks ago
- ☆26Updated last year
- Sphynx Hallucination Induction☆53Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆134Updated this week
- ☆105Updated last year
- Measuring the situational awareness of language models☆40Updated 2 years ago
- METR Task Standard☆173Updated last year
- we got you bro☆37Updated last year
- ☆29Updated last year
- ☆125Updated last year
- ☆112Updated last year
- An introduction to LLM Sampling☆79Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆35Updated 9 months ago