© 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. 64941
    Prev
    Next
    INDEX
    Explanations

    his desk or sleek design

    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
     Pocket
    -0.12
    Pocket
    -0.11
     handheld
    -0.11
     pocket
    -0.10
     turnout
    -0.10
     Doyle
    -0.10
    çĴ
    -0.10
    rooms
    -0.10
     Kara
    -0.09
     Oprah
    -0.09
    POSITIVE LOGITS
     desk
    0.45
     Desk
    0.36
    desk
    0.35
     desks
    0.35
    Desk
    0.34
    æ¡Į
    0.30
    -des
    0.27
     desktop
    0.24
     DES
    0.23
    _des
    0.22
    Activations Density 0.099%

    No Known Activations