© 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. 54400
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Conor
    -0.07
    ullan
    -0.07
    keit
    -0.07
     Bilim
    -0.07
     zbo
    -0.07
    è¡Ĩ
    -0.07
     Frequently
    -0.06
     restau
    -0.06
    ظÙĩ
    -0.06
    uchar
    -0.06
    POSITIVE LOGITS
     Guil
    0.06
     various
    0.06
     meanwhile
    0.06
    âĸį
    0.06
     fu
    0.06
    interpreter
    0.05
     a
    0.05
     Yuk
    0.05
    SEE
    0.05
    nul
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.