© 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. 43544
    Prev
    Next
    INDEX
    Explanations

    sarcasm, irony, dark humor

    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
     Laugh
    -0.13
     sly
    -0.10
    omid
    -0.09
     æ¯
    -0.09
     nond
    -0.09
     pr
    -0.09
     maneu
    -0.09
     insult
    -0.08
     cog
    -0.08
    ãĨį
    -0.08
    POSITIVE LOGITS
     sarc
    0.33
     tongue
    0.31
    iron
    0.28
    sar
    0.27
     Iron
    0.27
     iron
    0.25
     sat
    0.25
     irony
    0.25
    Iron
    0.25
     facet
    0.25
    Activations Density 0.229%

    No Known Activations