© 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. 93667
    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
    bour
    -0.07
    msgs
    -0.07
    kou
    -0.07
    ixin
    -0.07
    quan
    -0.07
    ibo
    -0.07
     embod
    -0.06
    Çİ
    -0.06
    ;display
    -0.06
    fang
    -0.06
    POSITIVE LOGITS
     involved
    0.06
    elden
    0.06
     Yoga
    0.06
    oenix
    0.06
     again
    0.06
    asma
    0.06
    Again
    0.06
     covid
    0.06
     Sne
    0.06
     sne
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.