© 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. 30993
    Prev
    Next
    INDEX
    Explanations

    mentions of diverse identities and ethnic backgrounds

    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
    isz
    -0.07
    argest
    -0.07
    ervas
    -0.06
    inet
    -0.06
     whilst
    -0.06
    vas
    -0.06
    ardash
    -0.06
    ãĤīãģĦ
    -0.06
     Manufact
    -0.06
    ãģ«ãģ¦
    -0.06
    POSITIVE LOGITS
    zcze
    0.07
     Weaver
    0.07
    ÑĥÑĩа
    0.07
    ufen
    0.07
    ncpy
    0.07
     ogs
    0.07
    soever
    0.07
    æ¢
    0.07
    PerPage
    0.06
     contexts
    0.06
    Activations Density 0.000%

    No Known Activations