© 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. 46033
    Prev
    Next
    INDEX
    Explanations

    coworkers, colleagues, and peers

    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
     Friends
    -0.11
     cousins
    -0.11
     clos
    -0.11
     friendship
    -0.11
     friends
    -0.10
     Cous
    -0.10
    ema
    -0.10
     pals
    -0.10
    oldt
    -0.09
    anean
    -0.09
    POSITIVE LOGITS
     colleagues
    0.30
     colleague
    0.29
     colle
    0.25
     coleg
    0.23
     co
    0.23
     fellow
    0.22
     colleg
    0.22
     кол
    0.22
     colleges
    0.20
    col
    0.19
    Activations Density 0.071%

    No Known Activations