© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    terms related to medical protocols and procedures

    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
    ÑĪов
    -0.06
    dice
    -0.06
    eton
    -0.06
    -ves
    -0.06
    ultiple
    -0.06
     verg
    -0.06
    cities
    -0.06
    ucht
    -0.06
    ashing
    -0.06
     Fare
    -0.06
    POSITIVE LOGITS
    /post
    0.10
    /pre
    0.09
    -period
    0.07
     Walters
    0.07
     Geh
    0.07
    ylan
    0.06
     period
    0.06
     dönemde
    0.06
    GMT
    0.06
     facto
    0.06
    Activations Density 0.012%

    No Known Activations