© 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. 73172
    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
     addCriterion
    -0.07
     dispatch
    -0.07
    435
    -0.06
    CORD
    -0.06
     DISPATCH
    -0.06
    ural
    -0.06
    unsch
    -0.06
     Zd
    -0.06
     #{@
    -0.06
    OMET
    -0.06
    POSITIVE LOGITS
     Tourism
    0.08
    ucher
    0.07
     flav
    0.06
     tourism
    0.06
    gan
    0.06
     -(
    0.06
    ustos
    0.06
    atoire
    0.06
    etik
    0.06
     -
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.