© 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. 38908
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainty in opinions or statements

    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
    dad
    -0.07
    esthetic
    -0.07
    ithub
    -0.06
    quier
    -0.06
    одаÑĢ
    -0.06
    .logs
    -0.06
    apixel
    -0.06
    ny
    -0.06
    ifer
    -0.06
     Dah
    -0.06
    POSITIVE LOGITS
     dun
    0.09
     Dun
    0.08
     depends
    0.08
     maybe
    0.07
    depends
    0.07
     Depends
    0.07
     depend
    0.07
    hausen
    0.07
    бол
    0.06
    elleicht
    0.06
    Activations Density 0.054%

    No Known Activations