The Llama 3 Herd of Models (Grattafiori et al., 2024)

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

• LLaMA-2 Model Familyconcept0.803
  Family of autoregressive transformer models used in all experiments; 7B, 13B, and 70B parameter sizes
• LLaMA / LLaMA2 / LLaMA3concept0.787
  Language model family used in cross-modal alignment experiments across multiple sizes
• Llama 3.3 70B is the most likely to take on a non-Assistant persona when steered, with even split between human and nonhuman portrayalsfinding0.767
  Model-specific difference in persona susceptibility
• Llama-3.3-70B exhibits internal consistency-checking mechanisms that operate during inferenceclaim0.752
  Central interpretive claim of the paper supported by causal ablation and activation evidence
• Llama 2concept0.752
  Meta's open large language model cited as an example of the class of models under discussion
• LLaMA3.1-8Bconcept0.743
  One of four LLMs selected for representation analysis; embedding dimension D=4096; used as demonstration model in scatter plots.
• LLaMA3.1-70Bconcept0.742
  One of four LLMs selected; larger model with D=8192 embedding dimension; analyzed across proportionally aligned layers.
• Scaling Laws for Activation Steering with Llama 2 Models and Refusal Mechanisms (Ali et al., 2025)concept0.741
  Related work finding larger models more resistant to steering, potentially consistent with ESR in 70B