© 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. 5682
    Prev
    Next
    INDEX
    Explanations

    themes and contexts

    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
     pe
    -0.09
    RelativeTo
    -0.09
     approaches
    -0.09
     approach
    -0.09
     heir
    -0.09
    804
    -0.09
     into
    -0.09
    604
    -0.09
     rum
    -0.09
    opi
    -0.08
    POSITIVE LOGITS
    /current
    0.10
    ä¸Ķ
    0.10
     Thema
    0.10
     theme
    0.09
     themes
    0.09
    piar
    0.09
     detriment
    0.09
    orio
    0.09
    themes
    0.09
    Theme
    0.09
    Activations Density 0.154%

    No Known Activations