© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23822
    Prev
    Next
    INDEX
    Explanations

    noun followed by a verb

    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
    ustr
    -0.10
    FileDialog
    -0.09
     Iso
    -0.09
    angep
    -0.09
    BoxLayout
    -0.09
    tober
    -0.09
    .infinity
    -0.08
    _ISO
    -0.08
     enjoy
    -0.08
     Willi
    -0.08
    POSITIVE LOGITS
     alone
    0.13
     really
    0.12
    ç®Ģ
    0.12
    羣æĺ¯
    0.12
     quả
    0.12
     rivals
    0.12
     certainly
    0.11
     simply
    0.11
     wirklich
    0.11
     absolutely
    0.11
    Activations Density 0.093%

    No Known Activations