© 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. 81972
    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
    ï¼ł
    -0.11
    ï¿¥
    -0.10
    ï¼ĭ
    -0.10
    živ
    -0.10
    .DropDown
    -0.10
     облиÑĩ
    -0.10
     ëĭ¤ìļ´ë°Ľê¸°
    -0.10
    òi
    -0.10
    INCLUDED
    -0.10
    .Extension
    -0.10
    POSITIVE LOGITS
    <|end_of_text|>
    0.07
     properties
    0.06
    ame
    0.05
    ani
    0.05
     By
    0.05
    --
    0.05
    ñas
    0.05
    as
    0.05
     Wind
    0.05
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.