© 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. 17377
    Prev
    Next
    INDEX
    Explanations

    references to making decisions or choices

    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
    pras
    -0.07
    iros
    -0.07
    ugo
    -0.07
    gree
    -0.07
    ừa
    -0.06
    erse
    -0.06
    _attachments
    -0.06
    lesen
    -0.06
    ltra
    -0.06
    ìĭľìĺ¤
    -0.06
    POSITIVE LOGITS
     chances
    0.12
     odds
    0.09
     then
    0.08
    then
    0.08
     Ryder
    0.07
     try
    0.07
     perhaps
    0.06
     chance
    0.06
     maybe
    0.06
    Then
    0.06
    Activations Density 0.017%

    No Known Activations