© 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. 15696
    Prev
    Next
    INDEX
    Explanations

    end of head tag

    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
     por
    -0.09
     ith
    -0.09
    tep
    -0.08
     ness
    -0.08
    ìĬ¬
    -0.08
    uya
    -0.08
     Statement
    -0.08
    *
    -0.08
     wee
    -0.08
     Ashe
    -0.08
    POSITIVE LOGITS
     div
    0.12
    ('</
    0.10
     endregion
    0.10
    ÂĢÂĢ
    0.10
    Å¡et
    0.09
     Giul
    0.09
    elerik
    0.09
    ("</
    0.09
    ofire
    0.09
    .addHandler
    0.09
    Activations Density 0.004%

    No Known Activations