© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39070
    Prev
    Next
    INDEX
    Explanations

    advice to women

    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
     gender
    -0.10
     sober
    -0.09
     people
    -0.09
    æł¸
    -0.09
     spouse
    -0.09
     statement
    -0.09
    350
    -0.09
     erotisch
    -0.09
     Nude
    -0.09
     boost
    -0.09
    POSITIVE LOGITS
     girls
    0.14
    girls
    0.11
     sisters
    0.11
    Girls
    0.11
     Girls
    0.11
     daughters
    0.10
     trust
    0.10
     yourselves
    0.10
     advice
    0.10
    Dear
    0.10
    Activations Density 0.048%

    No Known Activations