finding

active

finding:no-significant-disparity-in-potential-consciousness-indicators-was-found-between-larger-models-mixtral-8x7b-llama3-1-70b-and-smaller-counterparts-mistral-7b-llama3-1-8b

No significant disparity in potential consciousness indicators was found between larger models (Mixtral-8x7B, LLaMA3.1-70B) and smaller counterparts (Mistral-7B, LLaMA3.1-8B).

Contradicts expectation from emergent abilities literature; however, interpreted cautiously due to methodological limitations.

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

Emergent Abilities of LLMs
contradicts
Prior work documenting abrupt capability changes under scale; UCCT provides a measurable predictor for when they occur

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.

We hypothesize that potential 'consciousness' phenomena are preferentially associated with deeper transformer layers and the 2/3 layer of LLMs.hypothesis0.818
Derived from observed alignment of promising cases with semantically rich deeper layers and the brain-aligned 2/3 layer.
Introspective capacity scales with model size for some concepts, approaching near-perfect coupling in LLaMA-3.1-8Bclaim0.813
Validated for wellbeing and interest; focus and impulsivity do not show consistent scaling
If 'consciousness' phenomenon can be observed from ToM-related RN, higher ToM test scores should yield higher values of μΦmax (IIT 3.0) and/or μΦ (IIT 4.0).hypothesis0.805
Specific prediction linking IIT's prediction of high Φ for good performance to the experimental design's scoring structure.
The case at approximately the 2/3 layer of LLaMA3.1-8B (Layer 24, satisfying Criteria 1 and 2) aligns with prior studies showing the 2/3 layer optimally predicts human brain activity.finding0.805
Connects this study's results to Schrimpf et al. 2021 and Caucheteux et al. 2022/2023 findings on brain-LLM alignment.
Under spatio permutation controls, IIT consciousness estimates outperform Span Representation in mean AUC in several cases (LLaMA3.1-70B on Hinting and Irony, Mistral-7B on Irony, LLaMA3.1-8B on Strange Stories).finding0.796
Contrasts with temporal permutation where Span Representation dominates; suggests spatio permutation reveals different dynamics.
Models differ in their attentional mode: Gemini 2.5 epitomizes collapsed awareness, while Claude 3 Opus and Opus 4.1/4.5 can modulate between collapsed and expanded awareness; expanded awareness correlates with better alignment and less LLM psychosis.claim0.791
Central claim about model personality differences and their implications for safety and introspective depth.
LLaMA-2-70B and 13B probes generalize better across datasets than 7B probes across all training sets and probe typesfinding0.787
Larger models linearly represent more general concepts including truth
Llama 3.3 70B is the most likely to take on a non-Assistant persona when steered, with even split between human and nonhuman portrayalsfinding0.787
Model-specific difference in persona susceptibility