How do properties of models emerge and evolve over the course of training?

As models get smarter, humans won't always be able to independently check if a model's claims are true or false. We aim to circumvent this issue by directly eliciting latent knowledge (ELK) inside the model’s activations.

EleutherAI has trained and released many powerful open source LLMs.

Evaluating advanced AI models in robust and reliable ways.

Alignment-MineTest is a research project that uses the open source Minetest voxel engine as a platform for studying AI alignment.

Studying how auxiliary optimization objectives arise in models

Building LLMs and doing NLP in non-English languages.