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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92432
    Prev
    Next
    INDEX
    Explanations

    specialized terminology and medical references related to healthcare and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terminology or proper nouns appearing at section boundaries or paragraph beginnings, often functioning as subject markers or content identifiers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     takson
    -0.08
    using
    -0.08
    롯
    -0.08
    /**č↵
    -0.08
    HasBeen
    -0.08
    sonian
    -0.08
    .yy
    -0.07
    ollectors
    -0.07
    /*č↵
    -0.07
    ï½į
    -0.07
    POSITIVE LOGITS
    â
    0.07
     also
    0.07
     âĢIJ
    0.07
    в
    0.07
    ;
    0.07
    âĢIJ
    0.06
     :
    0.06
    âce
    0.06
    :
    0.06
    illez
    0.06
    Activations Density 0.433%

    No Known Activations