© 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. 4289
    Prev
    Next
    INDEX
    Explanations

    what would you like

    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
     Pron
    -0.10
    uko
    -0.09
     either
    -0.09
    530
    -0.08
     Canter
    -0.08
    ìĭľëĬĶ
    -0.08
    Ñĸг
    -0.08
    æĥij
    -0.08
    ада
    -0.08
    ought
    -0.08
    POSITIVE LOGITS
    zelf
    0.15
    uu
    0.15
    -même
    0.14
     be
    0.13
    /we
    0.12
     guys
    0.12
     ever
    0.12
    /us
    0.12
    åĢij
    0.12
     denn
    0.11
    Activations Density 0.094%

    No Known Activations