© 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. 85455
    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
     Toy
    -0.07
    aler
    -0.07
    olean
    -0.07
     Flake
    -0.07
     forg
    -0.06
    arra
    -0.06
    roduction
    -0.06
    ساÙĨÛĮ
    -0.06
     flaw
    -0.06
     mere
    -0.06
    POSITIVE LOGITS
    ça
    0.07
    WithDuration
    0.07
    μιÏĥ
    0.06
     VÅ¡ech
    0.06
    illisecond
    0.06
    mmo
    0.06
    Lua
    0.06
    _Execute
    0.06
     Orch
    0.06
     $#
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.