← Back to the feed
AI & softwareResearch findings

Maximally Activating Example Metamodel for Residual Stream Direction Interpretation

Original published 2026.11.06 03:54 KSTAdded to Blackdeck 2026.11.08 23:33 KST

What has changed?

A metamodel that converts residual stream directions into text exemplars that strongly activate them is proposed.

Key points

  1. We propose a metamodel, MAEM, to interpret residual stream directions by generating text exemplars that strongly activate them.
  2. MAEM maximizes cosine similarity between a given residual direction and activations of generated text, enabling precise interpretation.
  3. MAEM outperforms corpus search and NLA in activating held-out SAE features and recovering LoRA backdoor payloads.

Connect it to your work

It maximizes cosine similarity between a given direction and generated text activations to produce informative examples.

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivTowards interpreting any residual stream direction by scaling activation inversion