© 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. 19769
    Prev
    Next
    INDEX
    Explanations

    bubble sort

    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
     Solve
    -0.13
     ><?
    -0.09
     hex
    -0.08
    eres
    -0.08
     Reggie
    -0.08
    rian
    -0.08
     Pret
    -0.08
     Shower
    -0.08
     cape
    -0.08
    æ½®
    -0.08
    POSITIVE LOGITS
     sorting
    0.27
     sort
    0.26
     sorts
    0.25
     bubble
    0.25
     Bubble
    0.25
    sort
    0.25
    .sort
    0.23
    Bubble
    0.23
     ÑģоÑĢ
    0.23
    Sort
    0.22
    Activations Density 0.075%

    No Known Activations