© 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. 7888
    Prev
    Next
    INDEX
    Explanations

    take responsibility, discuss, try, listen

    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
    æīįèĥ½
    -0.12
     Walters
    -0.09
     Talent
    -0.09
    Enemies
    -0.09
    unch
    -0.09
     kre
    -0.09
     ach
    -0.09
    ovsky
    -0.09
     Commons
    -0.08
    amos
    -0.08
    POSITIVE LOGITS
     immediately
    0.15
     immedi
    0.12
     immediate
    0.12
    ãģĻãģIJ
    0.11
     simply
    0.11
     automáticamente
    0.11
     hemen
    0.11
     either
    0.10
     sofort
    0.10
     recourse
    0.10
    Activations Density 0.092%

    No Known Activations