© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 10582
    Prev
    Next
    INDEX
    Explanations

    normalize mental health stigma

    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
    Negative Logits
     Interracial
    -0.09
    owski
    -0.09
     threats
    -0.09
    paces
    -0.09
     peaceful
    -0.09
     Xm
    -0.09
     Morrow
    -0.09
    ynes
    -0.09
    isch
    -0.08
     peace
    -0.08
    POSITIVE LOGITS
     stigma
    0.34
     dest
    0.28
    igma
    0.20
     Dest
    0.19
     normalize
    0.18
     normalization
    0.18
    dest
    0.17
     normalized
    0.17
     Normalize
    0.17
    Normalize
    0.16
    Activations Density 0.109%

    No Known Activations