SOTAVerified

CBMAS: Cognitive Behavioral Modeling via Activation Steering

2026-01-03Code Available0· sign in to hype

Ahmed H. Ismail, Anthony Kuang, Ayo Akinkugbe, Kevin Zhu, Sean O'Brien

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering, which extends cognitive bias analysis from discrete before/after interventions to interpretable trajectories. By combining steering vector construction with dense α-sweeps, logit lens-based bias curves, and layer-site sensitivity analysis, our approach can reveal tipping points where small intervention strengths flip model behavior and show how steering effects evolve across layer depth. We argue that these continuous diagnostics offer a bridge between high-level behavioral evaluation and low-level representational dynamics, contributing to the cognitive interpretability of LLMs. Lastly, we provide a CLI and datasets for various cognitive behaviors at the project repository, https://github.com/shimamooo/CBMAS.

Reproductions