© 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. 4447
    Prev
    Next
    INDEX
    Explanations

    [noun] for

    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
    803
    -0.09
    aken
    -0.08
    çĪ
    -0.08
    utzer
    -0.08
    uguay
    -0.08
     ÙĦع
    -0.08
     Yorkers
    -0.08
     ÙĦÙģ
    -0.08
    endforeach
    -0.08
    ibase
    -0.08
    POSITIVE LOGITS
     for
    0.36
     für
    0.32
    สำหร
    0.31
     длÑı
    0.30
     dla
    0.26
    \tfor
    0.26
     untuk
    0.25
    for
    0.24
     براÛĮ
    0.24
     για
    0.24
    Activations Density 0.405%

    No Known Activations