acsresearch / interlab
☆18Updated 9 months ago
Alternatives and similar repositories for interlab:
Users that are interested in interlab are comparing it to the libraries listed below
- Interpreting how transformers simulate agents performing RL tasks☆79Updated last year
- Mechanistic Interpretability for Transformer Models☆50Updated 2 years ago
- A dataset of alignment research and code to reproduce it☆77Updated last year
- Machine Learning for Alignment Bootcamp☆72Updated 2 years ago
- (Model-written) LLM evals library☆18Updated 4 months ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ☆12Updated last week
- ☆132Updated 5 months ago
- METR Task Standard☆146Updated 2 months ago
- ☆54Updated 6 months ago
- General-Sum variant of the game Diplomacy for evaluating AIs.☆28Updated last year
- we got you bro☆35Updated 8 months ago
- ☆89Updated last month
- ☆19Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆88Updated 2 months ago
- Repo for the paper on Escalation Risks of AI systems☆38Updated last year
- ☆10Updated 9 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆199Updated last week
- ☆266Updated 9 months ago
- Stampy's copy of Alignment Research Dataset scraper☆12Updated last month
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆89Updated this week
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆49Updated this week
- ☆25Updated 11 months ago
- A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.☆24Updated this week
- Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments☆12Updated 3 years ago
- ☆26Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆100Updated last year
- Machine Learning for Alignment Bootcamp (MLAB).☆29Updated 3 years ago
- ☆31Updated 11 months ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆14Updated last month