© 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. 10635
    Prev
    Next
    INDEX
    Explanations

    training and trained models

    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
    amedi
    -0.10
     Laur
    -0.10
     Carol
    -0.09
     Tall
    -0.08
    èo
    -0.08
    ework
    -0.08
    PRINTF
    -0.08
     exert
    -0.08
    ilogy
    -0.08
     didReceiveMemoryWarning
    -0.08
    POSITIVE LOGITS
     training
    0.57
     Training
    0.45
     train
    0.42
    Training
    0.42
    training
    0.41
    è®Ń
    0.41
    -training
    0.38
    è¨ĵ
    0.35
     trained
    0.34
     TRAIN
    0.34
    Activations Density 0.071%

    No Known Activations