© 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. 59725
    Prev
    Next
    INDEX
    Explanations

    sexist jokes and descriptions

    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
     Rou
    -0.09
    å®Ļ
    -0.09
     Dish
    -0.08
     tender
    -0.08
    rif
    -0.08
     sesso
    -0.08
    á»Ĺi
    -0.08
     GENERATED
    -0.08
     mismatch
    -0.08
     unspecified
    -0.08
    POSITIVE LOGITS
    ennial
    0.10
     etc
    0.10
    ãģªãģ©ãģ®
    0.10
    ential
    0.10
     comments
    0.10
    بÙĪر
    0.09
    leanup
    0.09
     nor
    0.09
    jte
    0.09
     solic
    0.09
    Activations Density 0.016%

    No Known Activations