© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    lust and mischief

    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
     ejac
    -0.11
     sly
    -0.11
     neuken
    -0.10
    veis
    -0.10
     -*-č\n
    -0.10
    anth
    -0.09
    KANJI
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
    /******/
    -0.09
    -redux
    -0.09
    POSITIVE LOGITS
     sed
    0.16
     mischief
    0.16
     serious
    0.15
     innocent
    0.14
     Coy
    0.14
     devil
    0.13
     mysterious
    0.13
     wicked
    0.13
     evil
    0.13
     seriousness
    0.12
    Activations Density 0.028%

    No Known Activations