© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44714
    Prev
    Next
    INDEX
    Explanations

    illegal drugs and substances

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     arsen
    -0.10
     drunken
    -0.10
     Stout
    -0.10
     intoxicated
    -0.10
     antioxid
    -0.10
     Nob
    -0.09
    Contours
    -0.09
     Cumberland
    -0.09
     antibiotic
    -0.09
    ikan
    -0.09
    POSITIVE LOGITS
     drugs
    0.32
     substances
    0.30
     substance
    0.22
     Drugs
    0.21
     drug
    0.21
     Schedule
    0.19
     illegal
    0.18
     designer
    0.17
     stim
    0.17
     веÑīеÑģÑĤв
    0.17
    Activations Density 0.110%

    No Known Activations