© 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. 44139
    Prev
    Next
    INDEX
    Explanations

    leak-proof water bottle

    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
     Moff
    -0.09
     cas
    -0.09
     Bronze
    -0.09
     sticky
    -0.09
    ools
    -0.09
    sticky
    -0.09
     Sticky
    -0.09
     inject
    -0.09
     ãĤ»
    -0.08
     Twig
    -0.08
    POSITIVE LOGITS
     water
    0.18
     bottle
    0.17
     cups
    0.16
     flask
    0.16
     bottles
    0.16
     insulated
    0.16
    ottle
    0.16
     straw
    0.15
     drinking
    0.15
     carrying
    0.14
    Activations Density 0.061%

    No Known Activations