© 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. 85558
    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
    indle
    -0.07
    ,
    -0.06
     –
    -0.06
    -0.06
     (
    -0.06
    ENS
    -0.06
    418
    -0.06
    APP
    -0.06
     most
    -0.05
    erten
    -0.05
    POSITIVE LOGITS
    ulton
    0.07
    วย
    0.07
     Pam
    0.07
    [line
    0.07
    .vaadin
    0.07
    æĶ»
    0.07
    лада
    0.07
    @brief
    0.07
     بس
    0.07
    à¹Īà¸Ńà¸Ļ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.