© 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 EvalsExportsinterp-engineNEWAPI 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. 62718
    Prev
    Next
    INDEX
    Explanations

    references to governmental and organizational entities, particularly in the context of their regulations and impacts

    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
    аÑĤо
    -0.08
    ÑĢим
    -0.07
    éĩı
    -0.07
     xung
    -0.07
    çº
    -0.07
    ÙĦس
    -0.06
    à¥įपर
    -0.06
    ulle
    -0.06
    ëĭ
    -0.06
    ATO
    -0.06
    POSITIVE LOGITS
     functions
    0.07
     institution
    0.07
     itself
    0.07
     whose
    0.06
    ToFit
    0.06
    orners
    0.06
    lef
    0.06
    plorer
    0.06
     Gest
    0.06
     Reform
    0.06
    Activations Density 0.047%

    No Known Activations