© 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. 93226
    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
     seperate
    -0.06
    ầm
    -0.06
     Peek
    -0.06
    ZW
    -0.06
     Manor
    -0.06
     Bis
    -0.06
    :animated
    -0.06
    uw
    -0.06
     seper
    -0.05
    iero
    -0.05
    POSITIVE LOGITS
    gaard
    0.07
    osate
    0.07
    .sax
    0.07
    azole
    0.06
    undi
    0.06
    ursal
    0.06
    Looper
    0.06
    .fhir
    0.06
     Kür
    0.06
    _ASSUME
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.