© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103340
    Prev
    Next
    INDEX
    Explanations

    details related to medical history and patient examinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Medical documentation terminology patterns, particularly phrases related to patient history, symptom descriptions, and clinical assessments in healthcare records.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    iag
    -0.08
    ivre
    -0.07
    crest
    -0.07
    slope
    -0.07
    zens
    -0.07
     Lage
    -0.07
    opak
    -0.07
    hiba
    -0.07
    zen
    -0.07
    pong
    -0.07
    POSITIVE LOGITS
     history
    0.08
     prior
    0.07
     previous
    0.07
     recent
    0.07
     History
    0.07
    ooks
    0.07
    history
    0.07
     past
    0.06
     histories
    0.06
    History
    0.06
    Activations Density 0.027%

    No Known Activations