© 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. 73401
    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
     Jako
    -0.07
    tg
    -0.07
    ems
    -0.07
    aises
    -0.06
     eBooks
    -0.06
    otta
    -0.06
    obre
    -0.06
    ľ
    -0.06
    omo
    -0.06
     @}
    -0.06
    POSITIVE LOGITS
    Ñĵ
    0.07
     Qaeda
    0.06
     Mr
    0.06
     Ms
    0.06
    dbuf
    0.06
     Gal
    0.06
    etooth
    0.06
     ÙħÙĤاÙħ
    0.06
     quis
    0.06
    theid
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.