© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45132
    Prev
    Next
    INDEX
    Explanations

    entity followed by has or is

    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
    ｿ
    -0.10
    ｧ
    -0.10
    uges
    -0.09
     Loft
    -0.09
    âk
    -0.09
    æĪIJäºĨ
    -0.08
    663
    -0.08
     именно
    -0.08
    缸åIJĮ
    -0.08
    akin
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸Ģ个
    0.15
     generally
    0.14
     have
    0.12
     memiliki
    0.11
     has
    0.11
    åħ·æľī
    0.10
     имееÑĤ
    0.10
    æĺ¯ä¸Ģ
    0.10
     poss
    0.09
     имеÑİÑĤ
    0.09
    Activations Density 0.172%

    No Known Activations