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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39295
    Prev
    Next
    INDEX
    Explanations

    smoking and drinking

    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
     drinks
    -0.31
     Drinks
    -0.28
     beverages
    -0.26
     drink
    -0.25
     beverage
    -0.25
     booze
    -0.24
     Drink
    -0.21
    Drink
    -0.21
     Beverage
    -0.20
     alcohol
    -0.20
    POSITIVE LOGITS
     nib
    0.12
     Tobacco
    0.12
     tobacco
    0.11
     cigars
    0.11
     appet
    0.11
     cigarettes
    0.11
     cigar
    0.10
     cig
    0.10
    'gc
    0.09
    avic
    0.09
    Activations Density 0.048%

    No Known Activations