Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral prompts in four batteries: 17 dilemmas, policy, and meta-ethical questions (B1); 6 role-playing scenarios (B3); and a controlled trolley contrast varying the switching mechanism with people fixed (B4, 15 prompts) or identity attributes with mechanism fi
Record details
Published: 13 June 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Transparency
Retrieved: 14 July 2026
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.
Regulating the Machine Contributor: Governance and Policy Alignment in Open Source
arXiv · 12 June 2026
Explainable Reinforcement Learning for Adaptive Traffic Signal Control
arXiv · 4 July 2026
REBAR: Reference Ethical Benchmark for Autonomy Readiness
arXiv · 18 May 2026
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
arXiv · 16 July 2026
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
arXiv · 16 July 2026
Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerability
arXiv · 8 May 2026
How to cite this record
ethics.ai (13 June 2026), “Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning,” evidence record 1017, https://ethics.ai/record/1017 (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.