© 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. 116885
    Prev
    Next
    INDEX
    Explanations

    instructions related to medication usage and adherence

    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
    ãģıãģł
    -0.07
    atables
    -0.06
    ificent
    -0.06
    finalize
    -0.06
    usto
    -0.06
    á»iji
    -0.06
    exus
    -0.06
    ãĥ¯ãĥ¼
    -0.06
    inois
    -0.06
    üme
    -0.06
    POSITIVE LOGITS
     missed
    0.09
     Skip
    0.09
    .Skip
    0.08
     skipped
    0.08
     skipping
    0.07
     skip
    0.07
     chart
    0.07
    Skip
    0.07
     Skipping
    0.07
     Scheduled
    0.06
    Activations Density 0.003%

    No Known Activations