© 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. 27728
    Prev
    Next
    INDEX
    Explanations

    location of cities and airports across languages

    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
     ragaz
    -0.12
     surrounding
    -0.10
     nearby
    -0.10
    uze
    -0.10
     Surround
    -0.09
     surrounds
    -0.09
     Nearby
    -0.09
    ingham
    -0.08
    elden
    -0.08
    imb
    -0.08
    POSITIVE LOGITS
     located
    0.43
    located
    0.35
     Located
    0.33
    ä½įäºİ
    0.32
     befind
    0.31
    Located
    0.31
     locate
    0.30
     наÑħодиÑĤÑģÑı
    0.29
     location
    0.27
    ä½įæĸ¼
    0.26
    Activations Density 0.237%

    No Known Activations