arXiv AI August 11, 2026 By Yuqi Wu, Shengming Zhao, Jie Chen

When Is a Steerable Concept Representation Real? Measurement Confounds in a Cross-Family Audit of Neuroscience Parallels in LLMs

arXiv:2608. 08159v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly reported to exhibit human-like neural and cognitive signatures, including concept cells, mental number lines, and cognitive maps.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Jul 29

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.

By Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal, Dipesh Mahato

llms safety

arXiv AI

Aug 7

Small Foundation Models of Human Cognition and Behaviour

arXiv:2608. 05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions.

By Nick Oh, Fernand Gobet

llms fine-tuning

arXiv AI

Jul 2

NeuroCogMap Reveals Cognitive Organization of Large Language Models

arXiv:2607. 00397v1 Announce Type: cross Abstract: Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition.

By Zhongxiang Sun, Haolang Lu, Qiang Ma, Qi Li, Qipeng Wang, Liang Pang, Chenyu Liu, Qiankun Li, Hao Sun, Kun Wang, Yi Zeng, Jun Xu, Guoqi Li, Ji-Rong Wen

llms safety

arXiv AI

Aug 3

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.

By Matthew Nguyen, Kyle Cox, Austin Meek, Iv\'an Arcuschin

safety

arXiv Machine Learning

Aug 7

Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study

arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.

By Ayushi Agarwal

llms fine-tuning safety

arXiv AI

4d ago

Signatures of semantic search in the activations of large language models

arXiv:2609.35599v2 Announce Type: replace Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...

By Luke Leckie, Peter M. Todd, Jacob G. Foster

llms rag fine-tuning safety

One email a morning, machine-written

Related stories

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

Small Foundation Models of Human Cognition and Behaviour

NeuroCogMap Reveals Cognitive Organization of Large Language Models

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study

Signatures of semantic search in the activations of large language models