© 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. 80408
    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
    cox
    -0.06
    ingham
    -0.06
    è²Į
    -0.06
     зн
    -0.06
    ieee
    -0.06
    454
    -0.06
    ลาย
    -0.06
    ìĪĺë¡ľ
    -0.06
    rotch
    -0.06
    ÑĢой
    -0.06
    POSITIVE LOGITS
     Junk
    0.10
     junk
    0.08
     Maj
    0.07
    Narr
    0.07
    [](
    0.06
    webtoken
    0.06
    ä¹ĥ
    0.06
    kip
    0.06
    rea
    0.06
    vertime
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.