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

    Neuronpedia

    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. 125026
    Prev
    Next
    INDEX
    Explanations

    references to compliance and regulatory guidelines in healthcare

    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
    eza
    -0.07
     CORPOR
    -0.06
    UN
    -0.06
    imedia
    -0.06
     ÑĢез
    -0.06
     municip
    -0.06
    ÙĪØ´
    -0.06
     Weed
    -0.06
    914
    -0.06
     corpor
    -0.06
    POSITIVE LOGITS
     Medicare
    0.09
     CMS
    0.07
     Curry
    0.07
    azaar
    0.07
     USPS
    0.07
    .cms
    0.07
     Zur
    0.07
    ocoder
    0.07
    ussels
    0.07
     coding
    0.07
    Activations Density 0.009%

    No Known Activations