© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 55142
    Prev
    Next
    INDEX
    Explanations

    train.util usage

    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
    Not in Any Lists

    No Comments

    Negative Logits
    =tf
    -0.11
    .keras
    -0.10
    Pocket
    -0.09
     Malk
    -0.09
     subscription
    -0.09
     Tunnel
    -0.09
    andi
    -0.08
     Pocket
    -0.08
    subscription
    -0.08
     Jud
    -0.08
    POSITIVE LOGITS
     loss
    0.17
    loss
    0.15
     torch
    0.14
     optimizer
    0.14
    .zero
    0.13
    Loss
    0.13
     Loss
    0.13
    _loss
    0.13
     LOSS
    0.12
    .backward
    0.12
    Activations Density 0.012%

    No Known Activations