© 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. 105427
    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
     Tran
    -0.07
    Ñīин
    -0.06
     stuff
    -0.06
    icho
    -0.06
    iren
    -0.06
    InSection
    -0.06
     thing
    -0.06
    zd
    -0.06
     requ
    -0.05
    orget
    -0.05
    POSITIVE LOGITS
    ãģijãĤĮãģ©
    0.08
    -caret
    0.07
    /native
    0.07
    üc
    0.07
    hlen
    0.07
    .ease
    0.07
    encoded
    0.07
    inspace
    0.07
    PROTO
    0.07
    é«ĺéĢŁ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.