© 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. 61027
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical research and health-related data analysis

    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
     roughly
    -0.08
    Interop
    -0.07
    -0.07
     such
    -0.07
    apest
    -0.06
    [^
    -0.06
    ichever
    -0.06
    engin
    -0.06
    ibern
    -0.06
    246
    -0.06
    POSITIVE LOGITS
     âĢIJ
    0.09
    Ìģt
    0.09
    %C
    0.09
     č
    0.07
     EntityState
    0.07
    ...',
    0.07
     ApiController
    0.07
     /↵↵
    0.07
    دÙĨ
    0.07
    /remove
    0.07
    Activations Density 0.121%

    No Known Activations