question

active

question:is-experience-encoded-in-sequences-of-llm-representations-beyond-mere-knowledge-understanding-value-or-position

Is 'experience' encoded in sequences of LLM representations beyond mere 'knowledge,' 'understanding,' 'value,' or 'position'?

Secondary question motivating the IIT analysis; asks whether LLM hidden states contain something beyond propositional content.

Source paper

extracted_from

Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis

(2025) · Li, Jingkai

Neighborhood — ranked by edge-count

Concepts (1)

concept

Can 'Consciousness' Be Observed from Large Language Model (LLM) Internal States? Dissecting LLM Representations Obtained from Theory of Mind Test with Integrated Information Theory and Span Representation Analysis
introduces
The primary paper being extracted — applies IIT 3.0 and 4.0 to LLM representation sequences derived from ToM test data to investigate whether consciousness phenomena can be observed.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

When LLMs produce experience claims under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.779
The core interpretive question the paper narrows but cannot definitively answer
The paper does not claim that the LLM itself is the source of meaning and value, only that meaning can be discerned in its output.claim0.773
Clarification to avoid misinterpretation.
Sequences of contemporary Transformer-based LLM representations lack statistically significant indicators of observed 'consciousness' phenomena under the three stringent criteria.claim0.772
Primary conclusion of the study based on temporal permutation analysis failing all three criteria.
Are LLM emotion states encoded only selectively in token positions where they are operative, or in a more complex non-linear manner?question0.766
Question raised by Anthropic and partially addressed by this paper's persistence evidence
Linear Representation of Concepts in LLMsconcept0.761
The finding that interpretable concepts including character traits are encoded as linear directions in transformer residual streams
We hypothesize that LLMs represent correctness of arithmetic expressions differently from factual statements.hypothesis0.761
Core working hypothesis motivating the factual vs. arithmetic task split in the experimental design.
LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.760
Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
The LLM itself cannot 'experience' what it generates and therefore cannot possess consciousness; the RN is a higher-level construct that is independent of the LLM's architecture once representations are generated.claim0.757
Key theoretical position distinguishing analysis of representations from analysis of LLM architecture.