© 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. 9-LLAMASCOPE-RES-131K
    11. 98613
    Prev
    Next
    INDEX
    Explanations

    references to Madagascar and its political or economic context

    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
    <!--[
    -0.06
     hack
    -0.06
    .abort
    -0.06
     elev
    -0.06
    ocket
    -0.06
    ÑĥнкÑĤ
    -0.06
    ги
    -0.06
    份
    -0.06
     fur
    -0.06
    ates
    -0.05
    POSITIVE LOGITS
    à¹Īาà¸ĩ
    0.07
    /window
    0.07
    omba
    0.07
    yaw
    0.07
    wind
    0.07
     Redistribution
    0.07
    ucas
    0.07
    haus
    0.07
     Redistributions
    0.06
     вÑĥл
    0.06
    Activations Density 0.005%

    No Known Activations