© 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. 34477
    Prev
    Next
    INDEX
    Explanations

    World War II Japanese internment

    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
    abo
    -0.12
    ayi
    -0.10
     chast
    -0.10
     Kaplan
    -0.09
     paddle
    -0.09
     æ¯
    -0.09
    addle
    -0.09
     DIN
    -0.08
    Beam
    -0.08
    otre
    -0.08
    POSITIVE LOGITS
     intern
    0.23
     Intern
    0.19
    Intern
    0.18
    intern
    0.17
     camps
    0.15
     Enemy
    0.15
     enemy
    0.15
    enemy
    0.14
     Japanese
    0.14
    Japanese
    0.13
    Activations Density 0.013%

    No Known Activations