© 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. 63460
    Prev
    Next
    INDEX
    Explanations

    medications and drugs

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

    numbered list headings that introduce medication/treatment items, especially drug-category names followed by a colon and related dosing cues.

    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
     pharmac
    -0.16
     Pharmac
    -0.16
     drug
    -0.14
     pharmacist
    -0.14
     substance
    -0.13
     pharm
    -0.13
     chemical
    -0.12
     chemicals
    -0.12
     Pharm
    -0.12
    Drug
    -0.12
    POSITIVE LOGITS
     ant
    0.18
     NSA
    0.16
     stat
    0.15
     Concert
    0.13
     Dep
    0.13
     depot
    0.13
     ACE
    0.12
     anti
    0.12
     metam
    0.12
     aspir
    0.12
    Activations Density 0.078%

    No Known Activations