© 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. 40506
    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
    chers
    -0.06
    cher
    -0.06
     Macro
    -0.06
    upp
    -0.06
     Bench
    -0.06
     Goldberg
    -0.06
     BOOT
    -0.05
     ex
    -0.05
     Julien
    -0.05
    -to
    -0.05
    POSITIVE LOGITS
    undi
    0.08
    _VENDOR
    0.07
    ılıç
    0.07
    ä¿Ĥ
    0.07
    haus
    0.07
     ðŁĺī↵↵
    0.07
    ÑģÑİ
    0.07
    ÑĨо
    0.07
    ahan
    0.06
    èģ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.