© 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. 19429
    Prev
    Next
    INDEX
    Explanations

    Defence Ministry civilians

    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
     McKin
    -0.09
     Kund
    -0.09
     Sgt
    -0.09
    书记
    -0.09
    .va
    -0.09
    orest
    -0.09
    bp
    -0.09
     Sergeant
    -0.09
    umbed
    -0.09
    presso
    -0.09
    POSITIVE LOGITS
     bil
    0.12
     drill
    0.12
     Bil
    0.11
    obil
    0.10
     supern
    0.10
     trg
    0.10
     bounty
    0.10
     Gale
    0.10
     Cycl
    0.10
     Tome
    0.09
    Activations Density 0.007%

    No Known Activations