© 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. 38452
    Prev
    Next
    INDEX
    Explanations

    s followed by 'est", "ujet", "'é", "issy"

    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
     célib
    -0.10
     poil
    -0.10
     nouve
    -0.10
     Starr
    -0.10
    pec
    -0.10
     advoc
    -0.09
     ChÃŃ
    -0.09
    inator
    -0.09
     eiusmod
    -0.09
     Encore
    -0.09
    POSITIVE LOGITS
    0.12
    ied
    0.11
    rie
    0.11
    rs
    0.11
    ango
    0.10
    aper
    0.10
    sey
    0.10
    urs
    0.10
    aine
    0.09
    otte
    0.09
    Activations Density 0.022%

    No Known Activations