© 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. 73059
    Prev
    Next
    INDEX
    Explanations

    words and names that are characteristically associated with individuals or characters, often ending in specific suffixes

    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
    -packages
    -0.08
    fld
    -0.07
    utilus
    -0.07
    vÄĽ
    -0.07
    uido
    -0.07
    ambah
    -0.06
    itud
    -0.06
    ãģĬ
    -0.06
    baar
    -0.06
    eming
    -0.06
    POSITIVE LOGITS
    .gdx
    0.08
    ç¹Ķ
    0.06
     #__
    0.06
     ca
    0.06
    erville
    0.06
    ameda
    0.06
     comm
    0.06
     Honolulu
    0.06
    PRINTF
    0.06
    ismus
    0.06
    Activations Density 0.063%

    No Known Activations