© 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. 46032
    Prev
    Next
    INDEX
    Explanations

    international sanctions

    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
    åħ
    -0.11
     Hen
    -0.10
     treaty
    -0.10
     crackdown
    -0.10
    trak
    -0.09
    ania
    -0.09
     nast
    -0.09
     Soviets
    -0.09
     Sasha
    -0.09
    roma
    -0.09
    POSITIVE LOGITS
     sanctions
    0.35
     sanction
    0.26
    san
    0.22
     San
    0.20
     san
    0.19
     SAN
    0.16
    -san
    0.16
    _san
    0.16
    San
    0.16
     Western
    0.16
    Activations Density 0.057%

    No Known Activations