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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71028
    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
     Gly
    -0.08
     stuff
    -0.07
    ायद
    -0.07
    ruz
    -0.06
    klady
    -0.06
     Nich
    -0.06
     kys
    -0.06
    ITHER
    -0.06
    ETHER
    -0.06
    linger
    -0.06
    POSITIVE LOGITS
    avel
    0.07
    ç«ĭãģ¡
    0.07
     Bylo
    0.06
    lah
    0.06
    742
    0.06
    .Abstractions
    0.06
     اÙĦÙĨس
    0.06
     Yine
    0.06
    atures
    0.06
    owany
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.