© 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. 41846
    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
    ÅĽ
    -0.07
    606
    -0.07
    anio
    -0.07
     kır
    -0.07
    amax
    -0.06
    azzi
    -0.06
    zug
    -0.06
    tti
    -0.06
     ============================================================================↵
    -0.06
    .blob
    -0.06
    POSITIVE LOGITS
     staffers
    0.07
     longtime
    0.07
     Sands
    0.07
     staffer
    0.07
     plus
    0.06
     Hall
    0.06
    icao
    0.06
    AUDIO
    0.06
    xde
    0.06
    _gray
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.