© 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. 62569
    Prev
    Next
    INDEX
    Explanations

    folding something

    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
    æĭĶ
    -0.10
    oval
    -0.10
     Oval
    -0.09
     Rounds
    -0.09
     Fade
    -0.09
     Fey
    -0.09
    OLLOW
    -0.09
     Fuse
    -0.09
    .updateDynamic
    -0.09
     fizz
    -0.09
    POSITIVE LOGITS
     fold
    0.37
    æĬĺ
    0.33
    .fold
    0.32
     Fold
    0.31
    -fold
    0.30
    fold
    0.29
     folding
    0.29
    Fold
    0.28
     folds
    0.27
     folded
    0.25
    Activations Density 0.045%

    No Known Activations