© 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. 70365
    Prev
    Next
    INDEX
    Explanations

    expressions related to health issues and diagnostics

    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
    åķ
    -0.07
    lesson
    -0.06
    wand
    -0.06
     Sullivan
    -0.06
     ÑĥÑĢок
    -0.06
    fect
    -0.06
     previews
    -0.06
    gaard
    -0.06
     Teddy
    -0.06
     dür
    -0.06
    POSITIVE LOGITS
     diagnosis
    0.18
     Diagnosis
    0.16
     diagnose
    0.14
     diagnosed
    0.13
     diagn
    0.13
    -di
    0.12
     diagnoses
    0.12
    agnosis
    0.11
     diag
    0.11
    di
    0.11
    Activations Density 0.077%

    No Known Activations