© 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. 74982
    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
    unas
    -0.08
    anko
    -0.07
    etty
    -0.06
    ANGE
    -0.06
    延
    -0.06
    istra
    -0.06
    à¹īาà¸ĩ
    -0.06
     Exploration
    -0.06
    afen
    -0.06
    termin
    -0.06
    POSITIVE LOGITS
    夫
    0.07
    æł¡
    0.07
    enha
    0.07
    aser
    0.07
    .scalablytyped
    0.07
    bris
    0.07
    ação
    0.06
    -links
    0.06
    ANJI
    0.06
    iting
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.