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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125291
    Prev
    Next
    INDEX
    Explanations

    terms related to epidemiology and disease studies

    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
    geber
    -0.08
    erp
    -0.08
    tings
    -0.07
    STREAM
    -0.07
    ittings
    -0.07
    okud
    -0.07
    weather
    -0.07
    ownik
    -0.07
    .getInputStream
    -0.07
    /stretch
    -0.07
    POSITIVE LOGITS
    ally
    0.07
     studies
    0.07
    ological
    0.06
    emics
    0.06
    ouncer
    0.06
     inv
    0.06
     data
    0.06
     Aw
    0.06
    oin
    0.06
    aight
    0.06
    Activations Density 0.006%

    No Known Activations