© 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. 86667
    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
    orde
    -0.09
    iske
    -0.07
    aliz
    -0.07
    á»Ļt
    -0.06
    reon
    -0.06
    raž
    -0.06
    eve
    -0.06
     stamped
    -0.06
    ullo
    -0.06
    ÅĻeh
    -0.06
    POSITIVE LOGITS
     Trade
    0.09
     trade
    0.08
    trade
    0.07
    Trade
    0.07
    -trade
    0.07
     Foreign
    0.06
    igit
    0.06
    rex
    0.06
     sign
    0.06
     Horm
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.