© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1546
    Prev
    Next
    INDEX
    Explanations

    terms associated with health technology and patient engagement

    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
    ewart
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    .pnl
    -0.07
     cri
    -0.06
    eniable
    -0.06
    ingleton
    -0.06
    limitations
    -0.06
     caut
    -0.06
    avery
    -0.06
    acket
    -0.06
    POSITIVE LOGITS
    erde
    0.08
     exposure
    0.07
    otime
    0.07
    دة
    0.06
    ysl
    0.06
    unate
    0.06
     bubbles
    0.06
     Exposure
    0.06
     perceived
    0.06
     tert
    0.06
    Activations Density 0.138%

    No Known Activations