© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    technical or code syntax

    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
     [âĢ¦
    -0.10
    ãĢģãĢģ
    -0.10
    ô
    -0.09
     %[
    -0.09
     coquine
    -0.08
    ãĥ¼ãĥ¼
    -0.08
    Lorem
    -0.08
     \`
    -0.08
    FIXME
    -0.07
    .cleanup
    -0.07
    POSITIVE LOGITS
    .UnitTesting
    0.09
     -:-
    0.09
    argon
    0.09
    Ø´ÙħاÙĦÛĮ
    0.09
    âĶ¬
    0.08
    .moveToNext
    0.08
    .xyz
    0.08
    arto
    0.08
    iasi
    0.07
    ãģ¨ãģĨ
    0.07
    Activations Density 2.401%

    No Known Activations