© 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. 59603
    Prev
    Next
    INDEX
    Explanations

    UI actions and button clicks

    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
    .biz
    -0.09
     |:
    -0.09
    loquent
    -0.08
     craw
    -0.08
    TimeString
    -0.08
     âĹĦ
    -0.08
    upal
    -0.08
    YRO
    -0.08
     triple
    -0.07
     Eck
    -0.07
    POSITIVE LOGITS
     button
    0.16
    æĮīéĴ®
    0.12
    -button
    0.11
    ovat
    0.10
    _button
    0.10
    button
    0.10
    olin
    0.10
     æĮ
    0.10
    >NN
    0.09
    stab
    0.09
    Activations Density 0.069%

    No Known Activations