SOURCE-LINKED INTELLIGENCE

Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Lens convergence and causal head-level attribution to autonomously discover optimal steering parameters. Across three scales (1B x 3, 2-3B x 2, and 7-9B x 4), our engine achieves 16.7 percentage-point improvement on spam at 1B (standard deviation 4.7; 39 runs), with gains increasing to 21 to 42 percentage points at 7-9B across four architectures. On SST-2 sentiment, it achieves a 13.1 percentage-point improvement with z

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · Artificial Intelligence · 2026-09-17T17:16:31.000Z
arXiv · AI, language, vision and robotics · 2026-09-17T17:16:31.000Z

First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.