© 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. 7869
    Prev
    Next
    INDEX
    Explanations

    surveillance and survey operations

    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
    commons
    -0.10
    $MESS
    -0.09
     quoi
    -0.09
    illis
    -0.09
     commons
    -0.08
     Families
    -0.08
    bate
    -0.08
     downs
    -0.08
    tring
    -0.08
     electronics
    -0.08
    POSITIVE LOGITS
     surveillance
    0.15
     survey
    0.14
     military
    0.14
     Surveillance
    0.13
     homeland
    0.13
     surve
    0.13
     mapping
    0.13
     battlefield
    0.12
     surv
    0.12
     disaster
    0.12
    Activations Density 0.074%

    No Known Activations