© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40891
    Prev
    Next
    INDEX
    Explanations

    diagnostic terms and indicators related to diseases and medical conditions, particularly in epidemiological 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
    lav
    -0.06
    çļĦäºĭ
    -0.06
     Bid
    -0.06
     Slow
    -0.06
    æĭ¥æľī
    -0.06
    ç»ı
    -0.06
    elic
    -0.06
    .rc
    -0.06
    DataSetChanged
    -0.06
    째
    -0.06
    POSITIVE LOGITS
    monitor
    0.08
     staging
    0.08
     monitoring
    0.07
    onitor
    0.07
    -Za
    0.07
    -monitor
    0.07
     decision
    0.07
     decisions
    0.07
     Monitor
    0.07
     Evaluate
    0.07
    Activations Density 0.015%

    No Known Activations