© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41987
    Prev
    Next
    INDEX
    Explanations

    medications

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of medications and medication use in clinical contexts (including headings and multilingual text)

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alcohol
    -0.11
    esis
    -0.10
     Herbal
    -0.10
     detox
    -0.10
     heroin
    -0.09
     Marijuana
    -0.09
    MBProgressHUD
    -0.09
     caps
    -0.09
     Addiction
    -0.09
     Ammo
    -0.09
    POSITIVE LOGITS
     medication
    0.38
     medications
    0.36
     drugs
    0.29
     medicine
    0.29
    med
    0.24
    èį¯
    0.22
     medicines
    0.21
     pill
    0.21
     drug
    0.21
    èĹ¥
    0.20
    Activations Density 0.141%

    No Known Activations