© 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. 58137
    Prev
    Next
    INDEX
    Explanations

    is are becomes

    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
    zy
    -0.09
    inq
    -0.09
    usty
    -0.09
    -has
    -0.08
    ¯¯
    -0.08
    uppy
    -0.08
    تÙĪاÙĨ
    -0.08
    çĽijåIJ¬é¡µéĿ¢
    -0.08
    (&$
    -0.08
    AntiForgeryToken
    -0.08
    POSITIVE LOGITS
     wordt
    0.19
     wird
    0.18
     gets
    0.14
     edilir
    0.13
     Äijược
    0.13
     zost
    0.13
     viene
    0.13
     is
    0.13
     are
    0.13
     becomes
    0.12
    Activations Density 0.068%

    No Known Activations