© 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. 47306
    Prev
    Next
    INDEX
    Explanations

    places and landmarks

    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
     rendez
    -0.10
     relegated
    -0.10
    ascus
    -0.10
    258
    -0.09
     EntityState
    -0.09
     kims
    -0.09
     lẫn
    -0.08
     gì
    -0.08
     nud
    -0.08
    705
    -0.08
    POSITIVE LOGITS
     ÑĩÑĤобÑĭ
    0.15
     Äijá»ĥ
    0.14
    享
    0.14
    çľĭçľĭ
    0.12
    äºĨ解
    0.12
     where
    0.11
    欣
    0.10
     learns
    0.10
     sav
    0.10
     aby
    0.10
    Activations Density 0.067%

    No Known Activations