© 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. 72201
    Prev
    Next
    INDEX
    Explanations

    elements related to caregiver and healthcare provider interactions

    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
     âĹĦ
    -0.07
    (fullfile
    -0.07
    mrt
    -0.07
    rs
    -0.07
    lems
    -0.06
     Ou
    -0.06
    igor
    -0.06
    bine
    -0.06
    FORE
    -0.06
    deen
    -0.06
    POSITIVE LOGITS
     screening
    0.10
     screens
    0.08
     Screening
    0.08
    oyal
    0.07
     bro
    0.07
     routine
    0.07
    ologic
    0.07
     conversation
    0.07
     discussion
    0.07
     discussing
    0.07
    Activations Density 0.018%

    No Known Activations