© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30745
    Prev
    Next
    INDEX
    Explanations

    company attributes and descriptions

    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
     located
    -0.23
     Located
    -0.22
    located
    -0.21
    Located
    -0.19
    ä½įæĸ¼
    -0.18
    ä½įäºİ
    -0.17
     ubic
    -0.14
     situated
    -0.13
    locate
    -0.12
     ÙĪاÙĤع
    -0.11
    POSITIVE LOGITS
     proximity
    0.14
     easy
    0.13
    easy
    0.12
     clos
    0.12
     fácil
    0.12
     close
    0.11
     Kemal
    0.10
    ;element
    0.10
    æ´¥
    0.09
    Easy
    0.09
    Activations Density 0.077%

    No Known Activations