Astra can do crazy things without chain-of-thought. This is scary, but interpretability can help!
We made WorkspaceBench, an eval that tells you how well your interp tool surfaces the contents of the global workspace, i.e. the important intermediate variables in a forward pass.
Show more
J-lens is a powerful tool for surfacing workspace content, but it can be noisy in early layers. Can we uncover the true content of these layers?
We introduce the R-lens: a drop-in replacement for J-lens that produces clearer readouts on earlier layers.
Show more
