© 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. 64218
    Prev
    Next
    INDEX
    Explanations

    minority groups proportional

    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
     culturally
    -0.12
     Hispanics
    -0.10
     ethnicity
    -0.10
     ethn
    -0.10
     impoverished
    -0.10
     SAS
    -0.10
     racially
    -0.10
    ilder
    -0.10
     SOCK
    -0.10
     impover
    -0.10
    POSITIVE LOGITS
     groups
    0.27
    groups
    0.21
     Groups
    0.20
     minority
    0.19
    Minor
    0.19
     grupos
    0.18
    -groups
    0.18
    Groups
    0.18
     Minor
    0.18
    minor
    0.17
    Activations Density 0.066%

    No Known Activations