Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82931
    Prev
    Next
    INDEX
    Explanations

    references to animal prey and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ized
    -0.12
    eer
    -0.11
    izers
    -0.10
    izer
    -0.09
    ously
    -0.09
    aires
    -0.09
    ization
    -0.09
    ize
    -0.09
    aurus
    -0.09
    ised
    -0.09
    POSITIVE LOGITS
    adelphia
    0.10
    ington
    0.09
    ilateral
    0.08
    side
    0.08
    iful
    0.08
    space
    0.08
    iversary
    0.08
    geois
    0.08
    sy
    0.07
    iness
    0.07
    Activations Density 0.062%

    No Known Activations