© 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. 117618
    Prev
    Next
    INDEX
    Explanations

    references to antibiotic use and its measurement in medical 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
    reinterpret
    -0.07
    orem
    -0.06
    _MANY
    -0.06
     zel
    -0.06
    685
    -0.06
    rava
    -0.06
    ocket
    -0.06
    strstr
    -0.06
    sonian
    -0.06
     unless
    -0.06
    POSITIVE LOGITS
     various
    0.23
     Various
    0.18
     different
    0.17
    Various
    0.16
    åIJĦç§į
    0.15
     ÙħختÙĦÙģ
    0.15
     verschiedenen
    0.14
    different
    0.14
     verschied
    0.13
     ÑĢазлиÑĩнÑĭÑħ
    0.13
    Activations Density 0.166%

    No Known Activations