© 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. 72857
    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
    y
    -0.07
    yro
    -0.06
     pump
    -0.06
     Quote
    -0.06
    uitka
    -0.05
    ÙĪار
    -0.05
    zek
    -0.05
    pery
    -0.05
     Lump
    -0.05
    å¡ļ
    -0.05
    POSITIVE LOGITS
     Gür
    0.07
    iece
    0.07
    надлеж
    0.07
     èĭ¥
    0.07
    uther
    0.07
    æĵ¦
    0.07
    /loose
    0.07
    Terrain
    0.06
    Ģ
    0.06
    _processors
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.