© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    followed by "which"

    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
    489
    -0.10
    oni
    -0.10
     Hogan
    -0.09
    ild
    -0.09
    ulkan
    -0.09
     æİ
    -0.09
     Becker
    -0.09
    iverz
    -0.09
    elen
    -0.09
    jej
    -0.09
    POSITIVE LOGITS
     which
    0.20
    which
    0.19
     Which
    0.15
    为
    0.15
     ÙĪÙĩÙĪ
    0.15
    Which
    0.15
     olan
    0.14
    å°±æĺ¯
    0.14
     WHICH
    0.13
    ìŀIJìĿ¸
    0.13
    Activations Density 0.207%

    No Known Activations