© 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. 61263
    Prev
    Next
    INDEX
    Explanations

    discrimination or harassment

    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
     sexist
    -0.17
     misogyn
    -0.16
     sexism
    -0.14
     racist
    -0.14
     racially
    -0.13
     feminists
    -0.13
     misog
    -0.13
     racial
    -0.12
     feminist
    -0.12
     Homeland
    -0.11
    POSITIVE LOGITS
     Ston
    0.22
     Pride
    0.20
    GL
    0.20
     GL
    0.19
     acceptance
    0.19
     rainbow
    0.19
     pride
    0.19
     visibility
    0.18
     Visibility
    0.17
     Accept
    0.17
    Activations Density 0.094%

    No Known Activations