© 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. 77182
    Prev
    Next
    INDEX
    Explanations

    key details related to events, proposals, and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    isz
    -0.05
     England
    -0.05
    PTS
    -0.05
     Slow
    -0.05
     slow
    -0.05
    ét
    -0.05
    aska
    -0.05
     Press
    -0.05
    wayne
    -0.05
     ÙħستÙĤ
    -0.05
    POSITIVE LOGITS
     today
    0.14
     yesterday
    0.14
     tonight
    0.13
    today
    0.12
    ä»Ĭ天
    0.11
    ä»ĬæĹ¥
    0.11
     Yesterday
    0.11
     Thursday
    0.11
     Today
    0.10
     heute
    0.10
    Activations Density 0.014%

    No Known Activations