© 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. 42417
    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
     Jazz
    -0.07
    /apache
    -0.07
     living
    -0.06
     jazz
    -0.06
    entials
    -0.06
     reports
    -0.06
    ERA
    -0.06
    ãn
    -0.06
     answers
    -0.06
    antis
    -0.06
    POSITIVE LOGITS
    _interp
    0.08
    ØŃÙĨ
    0.07
     Conte
    0.07
    ónico
    0.07
    cpf
    0.07
     Ingredient
    0.07
    обов
    0.07
     ingredient
    0.07
    جاد
    0.07
     ضÙħÙĨ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.