© 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. 89478
    Prev
    Next
    INDEX
    Explanations

    terms and classes related to antibiotics and their usage

    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
    dlg
    -0.07
    ixel
    -0.07
    ypo
    -0.06
    formation
    -0.06
     VERBOSE
    -0.06
    ibrated
    -0.06
    estar
    -0.06
    105
    -0.06
    oke
    -0.06
    utura
    -0.06
    POSITIVE LOGITS
    misc
    0.10
    Misc
    0.09
    /misc
    0.08
    ritz
    0.07
     Uncategorized
    0.07
     others
    0.07
     miscellaneous
    0.07
     misc
    0.07
    æŀľ
    0.07
     اÙĦأخرÙī
    0.07
    Activations Density 0.054%

    No Known Activations