© 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. 28569
    Prev
    Next
    INDEX
    Explanations

    terms related to gastrointestinal and urinary tract infections caused by specific bacteria

    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
    hea
    -0.06
    olid
    -0.06
     ju
    -0.06
    TI
    -0.06
    uble
    -0.06
     disturbed
    -0.06
    uju
    -0.06
    jis
    -0.06
    pal
    -0.06
    aney
    -0.06
    POSITIVE LOGITS
    ewan
    0.09
     bacteria
    0.09
    micro
    0.07
    Micro
    0.07
     shedding
    0.07
    _micro
    0.07
    ipeg
    0.07
     Micro
    0.07
    Ỽp
    0.07
    aceae
    0.06
    Activations Density 0.057%

    No Known Activations