© 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 EvalsExportsAPI 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. 59344
    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
    _strip
    -0.07
     Stam
    -0.07
    rip
    -0.07
    akis
    -0.07
    orman
    -0.07
    íļį
    -0.07
    _clause
    -0.07
     swingers
    -0.07
     dicks
    -0.06
    aller
    -0.06
    POSITIVE LOGITS
     -*-č↵
    0.07
    olec
    0.07
    dre
    0.06
     Establishment
    0.06
     Esper
    0.06
    elian
    0.06
    URRE
    0.06
     Soros
    0.06
     drib
    0.06
    uzzi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.