© 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. 94891
    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
     Rap
    -0.07
    ä¼ı
    -0.06
    lein
    -0.06
     odp
    -0.06
    ccd
    -0.06
    antor
    -0.06
     impl
    -0.06
     GLES
    -0.05
    _IMPL
    -0.05
     vene
    -0.05
    POSITIVE LOGITS
    .cgi
    0.09
    cpy
    0.07
    iqueta
    0.07
    agher
    0.07
    ReadWrite
    0.07
    addtogroup
    0.07
    urses
    0.06
    Fluid
    0.06
     $"{
    0.06
    aight
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.