© 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. 15-LLAMASCOPE-RES-131K
    11. 87876
    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
    oola
    -0.08
    olean
    -0.07
    unan
    -0.07
    èĩªæ²»
    -0.07
    ReLU
    -0.07
    ancer
    -0.07
    yas
    -0.06
    )prepare
    -0.06
    velt
    -0.06
    æł
    -0.06
    POSITIVE LOGITS
     Hava
    0.07
    .googlecode
    0.06
    .persist
    0.06
    grab
    0.06
    ienne
    0.06
    ivan
    0.06
    ften
    0.06
    throp
    0.06
    ientos
    0.06
    gnore
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.