© 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. 24191
    Prev
    Next
    INDEX
    Explanations

    racial and social commentary

    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
     Latinos
    -0.10
     Greeks
    -0.10
     Koreans
    -0.10
     fer
    -0.09
     Catholics
    -0.09
    ｨ
    -0.09
    ï½£
    -0.09
     Saudis
    -0.09
     coquine
    -0.09
    Opaque
    -0.09
    POSITIVE LOGITS
     white
    0.13
     certain
    0.11
     races
    0.11
     superiority
    0.10
     race
    0.10
    移
    0.10
     Rap
    0.10
    ommen
    0.10
     bir
    0.10
     White
    0.10
    Activations Density 0.119%

    No Known Activations