© 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. 7900
    Prev
    Next
    INDEX
    Explanations

    biographical educational history

    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
     GetLastError
    -0.09
     imm
    -0.09
     Kang
    -0.09
     Mattis
    -0.09
     âĩĴ
    -0.09
    erts
    -0.09
    LEC
    -0.09
     Gim
    -0.09
    åĻ
    -0.08
     Koch
    -0.08
    POSITIVE LOGITS
     Obama
    0.20
     Barack
    0.19
    Obama
    0.17
     Chicago
    0.17
     Luo
    0.16
     Hawaii
    0.15
    Chicago
    0.15
     Michelle
    0.14
     Kenya
    0.14
     Dreams
    0.13
    Activations Density 0.021%

    No Known Activations