© 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. 4488
    Prev
    Next
    INDEX
    Explanations

    phrases or entities related to business and personal interactions

    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
    rame
    -0.07
    misc
    -0.07
    à¥ĭà¤ļ
    -0.07
    èĤ©
    -0.06
     Basket
    -0.06
     reservations
    -0.06
    acle
    -0.06
    _SR
    -0.06
     miscellaneous
    -0.06
    elo
    -0.06
    POSITIVE LOGITS
    jvu
    0.08
    XYZ
    0.06
    -lnd
    0.06
     Böl
    0.06
    ower
    0.06
     cla
    0.06
    olum
    0.06
     myself
    0.06
     dated
    0.06
     QStringLiteral
    0.06
    Activations Density 0.000%

    No Known Activations