All in a Day's Work: SAEs, MAX Engine, and a Memory That Thinks

This site does not allow itself to be embedded. You can still read it on the original site — the toolbar below keeps your place in the directory.

Three things landed this week. They look unrelated on the surface — an interpretability dataset, an infrastructure fix, a memory experiment — but they’re all the same project from different angles: figuring out what a 31B-parameter model is actually doing inside, and using that understanding to make it do more. The full technical writeups live on the Light of Baldr site. This post is the…

Read on lab-stack.com ↗