© 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. 77190
    Prev
    Next
    INDEX
    Explanations

    keywords related to market data, trade, and production in various industries

    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
    еви
    -0.07
    StringEncoding
    -0.07
    ÑģиÑĤ
    -0.07
    æ³ī
    -0.07
    llib
    -0.07
    elpers
    -0.06
    akov
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    umbing
    -0.06
     Searches
    -0.06
    POSITIVE LOGITS
     information
    0.14
     details
    0.12
     info
    0.11
    ä¿¡æģ¯
    0.09
    details
    0.09
     detail
    0.09
    -related
    0.08
    information
    0.08
     Information
    0.08
     breakdown
    0.07
    Activations Density 0.074%

    No Known Activations