How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate and amplifier are single heads; at larger scale they become bands of heads across adjacent layers. The gate contributes under 1% of output DLA, yet interchange testing (p = 120 detects the same motif in twelve models from six labs (2B to 72B), though specific

Related evidence

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (6 April 2026), “How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models,” evidence record 6333, https://ethics.ai/record/6333 (originally published by arXiv).

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.