© 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. 92991
    Prev
    Next
    INDEX
    Explanations

    references to medical studies and analyses involving antibiotics and their use in treating infections

    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
    tember
    -0.07
     lucr
    -0.07
     Thing
    -0.07
    ças
    -0.07
    bjerg
    -0.06
    ething
    -0.06
     thang
    -0.06
    edith
    -0.06
    adu
    -0.06
    æľĹ
    -0.06
    POSITIVE LOGITS
    lick
    0.07
    rob
    0.07
    van
    0.06
    ulin
    0.06
    /git
    0.06
    arget
    0.06
    ibur
    0.06
    uls
    0.06
    Ĵ
    0.06
    ãĥ¡ãĥ³ãĥĪ
    0.06
    Activations Density 0.041%

    No Known Activations