© 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. 8142
    Prev
    Next
    INDEX
    Explanations

    attack on civilian targets

    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
     pur
    -0.11
     fighting
    -0.10
    ctl
    -0.10
    386
    -0.10
    _indent
    -0.09
    868
    -0.09
     ä½ı
    -0.09
    ucc
    -0.09
    etes
    -0.09
     cann
    -0.09
    POSITIVE LOGITS
     targets
    0.27
    targets
    0.21
     Targets
    0.21
     undef
    0.20
     innocent
    0.17
    缮æłĩ
    0.16
    Targets
    0.16
     civilians
    0.16
     target
    0.16
    undef
    0.15
    Activations Density 0.083%

    No Known Activations