© 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. 11305
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

    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
     Hurricane
    -0.09
     lipid
    -0.09
     Comcast
    -0.09
    ï¾ĺ
    -0.08
     Rutgers
    -0.08
     cape
    -0.08
     Rural
    -0.08
     Wat
    -0.08
    .Dataset
    -0.08
    ाà¤ĸ
    -0.08
    POSITIVE LOGITS
     LA
    0.48
     Los
    0.46
    LA
    0.40
    Los
    0.39
     Angeles
    0.30
    .LA
    0.30
     UCLA
    0.29
     LAP
    0.28
     USC
    0.27
    _LA
    0.26
    Activations Density 0.055%

    No Known Activations