concept
active
concept:mixture-of-experts-moeMixture-of-Experts (MoE)
Architecture of Mixtral-8x7B; uses sparse expert routing affecting how hidden states are computed across layers.
Neighborhood — ranked by edge-count
Concepts (2)
concept
- 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.
- Mixtral-8x7BimplementsOne of four LLMs selected; Mixture-of-Experts model; had substantial sample loss under IIT 4.0 due to PyPhi network initialization issues.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Selection strategy that adapts which demonstrations carry signal; in UCCT terms increases effective ρd
- Program that supported Tim Hua and Andrew Qin during this research.
- Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (Bricken et al., 2023)concept0.730Foundational SAE mechanistic interpretability paper
- Demonstration that model-level priors (not parameter-level knowledge) suffice for immediate transfer
- Probabilistic behaviour of an ensemble used to derive the free-energy principle.
- Interpretability property where a latent feature represents a single semantic concept; benchmarked across architectures.
- Ian Goodfellow quote used to illustrate the pre-paradigmatic state of interpretability research
- The widespread belief that only trained professionals can design environments, which disempowers ordinary people and prevents adaptation.