© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128284
    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
    .Accessible
    -0.08
     plá
    -0.08
    онÑĤ
    -0.07
    òi
    -0.07
    ertino
    -0.07
    /Foundation
    -0.07
    Configurer
    -0.07
    clare
    -0.07
    _android
    -0.07
    ÂĢ
    -0.07
    POSITIVE LOGITS
     thousand
    0.07
    0.07
    oli
    0.06
     till
    0.05
     Solo
    0.05
     based
    0.05
    umat
    0.05
    onis
    0.05
     major
    0.05
    dera
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.