benchmark-instructed-control-over-model-s-own-activations TEC-0096 · proposedBenchmark instructed control over a model's own activations
Scores a model on six measures of how well it modulates its residual-stream projection onto a concept direction on instruction (engage, suppress, intensity dial, temporal placement, token coverage, layer targeting), combined into one geomet
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Scores a model on six measures of how well it modulates its residual-stream projection onto a concept direction on instruction (engage, suppress, intensity dial, temporal placement, token coverage, layer targeting), combined into one geomet Filed by the drafting stage from Measuring Activation Control in Large Language Models (2608.21664) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Applied to 25 open-weight models; scores ranged 0.059-0.538, did not track parameter count, and rose across Olmo training checkpoints; monitor-evasion results reported separately against four monitor families.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.