© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83059
    Prev
    Next
    INDEX
    Explanations

    references to inspiration and influential figures in art and culture

    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
    yg
    -0.07
    dae
    -0.07
    bara
    -0.07
    inea
    -0.06
    ToJson
    -0.06
    aptive
    -0.06
    piel
    -0.06
    Dual
    -0.06
    inci
    -0.06
    pline
    -0.06
    POSITIVE LOGITS
     idea
    0.08
    afort
    0.07
     inspiration
    0.07
     inspir
    0.07
     ideas
    0.06
     Collections
    0.06
    _beh
    0.06
     many
    0.06
    OLS
    0.06
    .beh
    0.06
    Activations Density 0.014%

    No Known Activations