© 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. 38327
    Prev
    Next
    INDEX
    Explanations

    neural network layers and activations

    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
    inel
    -0.09
     unl
    -0.09
    bons
    -0.09
     torchvision
    -0.09
     superClass
    -0.09
     Schiff
    -0.09
    éĹ»
    -0.09
    ater
    -0.08
     Torch
    -0.08
     Abed
    -0.08
    POSITIVE LOGITS
    alth
    0.10
    .relu
    0.09
    relu
    0.09
     Dense
    0.09
    utf
    0.09
    rve
    0.09
    adam
    0.09
    ritz
    0.09
     identity
    0.09
     medi
    0.09
    Activations Density 0.018%

    No Known Activations