© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18783
    Prev
    Next
    INDEX
    Explanations

    joke or why

    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
    Negative Logits
    å¼ĭ
    -0.10
     оÑĢганиза
    -0.10
    åŃ©
    -0.10
     имÑĥ
    -0.10
     wax
    -0.09
     Dann
    -0.09
     ÑģоÑħÑĢа
    -0.09
     Wax
    -0.08
    illes
    -0.08
     Monkey
    -0.08
    POSITIVE LOGITS
     once
    0.14
     why
    0.12
    为ä»Ģä¹Ī
    0.11
     one
    0.10
    æľīä¸Ģ
    0.10
     Once
    0.10
    once
    0.09
     ëĦ¤ìĿ´íĬ¸
    0.09
     один
    0.09
     Dud
    0.09
    Activations Density 0.153%

    No Known Activations