© 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. 104917
    Prev
    Next
    INDEX
    Explanations

    terminology related to drugs and medical classifications

    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
    uo
    -0.07
    hart
    -0.06
    ãĥĭãĤ¢
    -0.06
    Ïĥη
    -0.06
     Nationwide
    -0.06
    inding
    -0.06
    #__
    -0.06
     toy
    -0.05
    ubo
    -0.05
    pic
    -0.05
    POSITIVE LOGITS
     within
    0.15
    within
    0.13
     Within
    0.13
    Within
    0.12
     members
    0.12
    members
    0.11
    _within
    0.11
     thuá»Ļc
    0.11
     Members
    0.10
     member
    0.09
    Activations Density 0.127%

    No Known Activations