© 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. 5548
    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
    oyer
    -0.06
     ><?
    -0.06
    _suite
    -0.06
     commanded
    -0.06
    áºŃu
    -0.06
    /command
    -0.06
    leme
    -0.06
    обов
    -0.05
     CSC
    -0.05
    resents
    -0.05
    POSITIVE LOGITS
    mite
    0.07
    hend
    0.07
    amina
    0.07
     slots
    0.07
    udeau
    0.07
    plevel
    0.07
    ÏĦει
    0.07
    анка
    0.07
    rowable
    0.07
    ackage
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.