© 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. 18662
    Prev
    Next
    INDEX
    Explanations

    enjoy a treat

    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
    eler
    -0.11
    olik
    -0.10
     munch
    -0.10
     Appet
    -0.09
    TestCase
    -0.09
    ulet
    -0.09
     appet
    -0.09
     огÑĢа
    -0.09
     ApplicationException
    -0.09
    -thumbnails
    -0.09
    POSITIVE LOGITS
     treat
    0.52
     Treat
    0.46
     treats
    0.42
     treating
    0.41
     spl
    0.38
     treated
    0.33
    spl
    0.28
     reward
    0.27
     pam
    0.27
     Spl
    0.26
    Activations Density 0.092%

    No Known Activations