© 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. 79639
    Prev
    Next
    INDEX
    Explanations

    gambling-related terminology, particularly around bets and payouts

    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
     Thá»ĭ
    -0.07
    ender
    -0.07
     thá»ĭ
    -0.06
    TRS
    -0.06
    uluk
    -0.06
    ãģ«ãģĤãĤĭ
    -0.06
    ýt
    -0.06
     Marsh
    -0.06
    ÄĽr
    -0.06
    ologne
    -0.06
    POSITIVE LOGITS
     autob
    0.06
     input
    0.06
    agus
    0.06
    unt
    0.06
     tung
    0.06
    анÑĮ
    0.06
     gent
    0.06
     dirt
    0.06
     Stra
    0.06
    rido
    0.06
    Activations Density 0.004%

    No Known Activations