© 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. 93311
    Prev
    Next
    INDEX
    Explanations

    mentions of monetary values and financial figures

    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
    .plist
    -0.06
    ichte
    -0.06
     lux
    -0.06
    vá
    -0.06
    ruc
    -0.06
    413
    -0.06
    .misc
    -0.06
     Dice
    -0.06
    forge
    -0.06
     numbering
    -0.06
    POSITIVE LOGITS
    ì§ľ
    0.09
    achs
    0.08
    æ´ĭ
    0.07
    uros
    0.07
    å·¦åı³
    0.07
    ["@
    0.07
    trecht
    0.07
    âĢ³
    0.06
    theValue
    0.06
     नà¤ķ
    0.06
    Activations Density 0.031%

    No Known Activations