© 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. 39262
    Prev
    Next
    INDEX
    Explanations

    terms associated with mechanical function and patient care in healthcare contexts

    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
    ầm
    -0.07
    ivr
    -0.07
    ä¸Ī
    -0.06
    alim
    -0.06
    ocha
    -0.06
    ysa
    -0.06
     outer
    -0.06
     osm
    -0.06
    _equiv
    -0.06
    erdale
    -0.06
    POSITIVE LOGITS
     gravity
    0.12
     Gravity
    0.10
    gravity
    0.10
    Gravity
    0.09
     grav
    0.08
    GRA
    0.07
    Statics
    0.07
     gravitational
    0.07
    .gravity
    0.07
     RectTransform
    0.06
    Activations Density 0.011%

    No Known Activations