Cover Image

Convergent Linear Representations of Emergent Misalignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Soligo, Anna, Turner, Edward, Rajamanoharan, Senthooran, Nanda, Neel
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Model Organisms for Emergent Misalignment
by: Turner, Edward, et al.
Published: (2025)

Emergent Misalignment is Easy, Narrow Misalignment is Hard
by: Soligo, Anna, et al.
Published: (2026)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
by: Ferrando, Javier, et al.
Published: (2024)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
by: Kantamneni, Subhash, et al.
Published: (2025)

Thought Branches: Interpreting LLM Reasoning Requires Resampling
by: Macar, Uzay, et al.
Published: (2025)

How Well Do Models Follow Their Constitutions?
by: Jakkli, Arya, et al.
Published: (2026)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, et al.
Published: (2025)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Improving Dictionary Learning with Gated Sparse Autoencoders
by: Rajamanoharan, Senthooran, et al.
Published: (2024)

Towards eliciting latent knowledge from LLMs with mechanistic interpretability
by: Cywiński, Bartosz, et al.
Published: (2025)

Subliminal Learning Is Steering Vector Distillation
by: Blank, Camila, et al.
Published: (2026)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
by: Lieberum, Tom, et al.
Published: (2024)

Simple Mechanistic Explanations for Out-Of-Context Reasoning
by: Wang, Atticus, et al.
Published: (2025)

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
by: Arturi, Daniel Aarao Reis, et al.
Published: (2025)

Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
by: Soligo, Anna, et al.
Published: (2025)

Dense SAE Latents Are Features, Not Bugs
by: Sun, Xiaoqing, et al.
Published: (2025)

Explorations of Self-Repair in Language Models
by: Rushing, Cody, et al.
Published: (2024)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
by: Zhang, Fred, et al.
Published: (2023)

Eliciting Secret Knowledge from Language Models
by: Cywiński, Bartosz, et al.
Published: (2025)

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
by: Rajamanoharan, Senthooran, et al.
Published: (2024)

BatchTopK Sparse Autoencoders
by: Bussmann, Bart, et al.
Published: (2024)

In-Training Defenses against Emergent Misalignment in Language Models
by: Kaczér, David, et al.
Published: (2025)

Understanding Emergent Misalignment via Feature Superposition Geometry
by: Minegishi, Gouki, et al.
Published: (2026)

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
by: Arnold, Julian, et al.
Published: (2025)

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
by: Mushtaq, Erum, et al.
Published: (2025)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
by: Bussmann, Bart, et al.
Published: (2025)

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
by: Chua, James, et al.
Published: (2025)

Persona-Model Collapse in Emergent Misalignment
by: Costa, Davi Bastos, et al.
Published: (2026)

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
by: Askin, Baris, et al.
Published: (2026)

Understanding Reasoning in Thinking Language Models via Steering Vectors
by: Venhoff, Constantin, et al.
Published: (2025)

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
by: Jiang, Nick, et al.
Published: (2025)

Base Models Know How to Reason, Thinking Models Learn When
by: Venhoff, Constantin, et al.
Published: (2025)

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
by: Betley, Jan, et al.
Published: (2025)

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs
by: Dickson, Craig
Published: (2025)

Persona Features Control Emergent Misalignment
by: Wang, Miles, et al.
Published: (2025)

Thought Anchors: Which LLM Reasoning Steps Matter?
by: Bogdan, Paul C., et al.
Published: (2025)

Overtrained, Not Misaligned
by: Schreiber, Joel, et al.
Published: (2026)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
by: Giordani, Jeremiah
Published: (2025)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)