© 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. 24414
    Prev
    Next
    INDEX
    Explanations

    requests for sexual favors

    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
     åıĪ
    -0.09
     cong
    -0.09
     Contrib
    -0.09
     Gilbert
    -0.09
    coe
    -0.09
     Mandal
    -0.09
     Baylor
    -0.08
    ubit
    -0.08
    sel
    -0.08
     MessageBoxButtons
    -0.08
    POSITIVE LOGITS
     fulfilled
    0.13
     fullfile
    0.11
     denied
    0.10
    (Request
    0.10
     granted
    0.10
     request
    0.10
     satisfied
    0.10
    onya
    0.10
     unanswered
    0.10
     Gir
    0.09
    Activations Density 0.139%

    No Known Activations