© 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. 75285
    Prev
    Next
    INDEX
    Explanations

    references to literary works and their origins

    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
    áp
    -0.07
    ENCHMARK
    -0.07
    ça
    -0.07
    ázky
    -0.07
    .ribbon
    -0.07
    жи
    -0.07
     spons
    -0.06
    екаÑĢ
    -0.06
    ofi
    -0.06
    è±
    -0.06
    POSITIVE LOGITS
    inz
    0.07
    inke
    0.07
    IT
    0.07
    406
    0.07
     Shea
    0.06
     Atlas
    0.06
    506
    0.06
    herits
    0.06
     wr
    0.06
    773
    0.06
    Activations Density 0.001%

    No Known Activations