© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30223
    Prev
    Next
    INDEX
    Explanations

    offensive language and profanity

    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
    abus
    -0.10
     pronounce
    -0.09
     suspicious
    -0.09
    linky
    -0.09
     organ
    -0.09
    ÙĬØ«
    -0.09
     stolen
    -0.09
    aida
    -0.08
     cla
    -0.08
     Oy
    -0.08
    POSITIVE LOGITS
     prof
    0.17
     PG
    0.14
     offensive
    0.14
     Offensive
    0.13
     language
    0.13
     Language
    0.13
    prof
    0.13
     censor
    0.13
     curse
    0.12
     ìļķ
    0.12
    Activations Density 0.232%

    No Known Activations