© 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. 11596
    Prev
    Next
    INDEX
    Explanations

    Cape, 2, streets, alice

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -0.10
     Mov
    -0.10
     deck
    -0.10
     Horn
    -0.10
     Core
    -0.10
     Cov
    -0.10
     decks
    -0.09
     Rom
    -0.09
     Alexandria
    -0.09
     Daw
    -0.09
    POSITIVE LOGITS
     Markets
    0.11
     Krak
    0.10
     jewish
    0.10
     Jewish
    0.09
    ียà¸ĩà¹ĥหม
    0.09
    _topology
    0.09
    cus
    0.09
    loon
    0.09
    _permalink
    0.09
    anship
    0.09
    Activations Density 0.028%

    No Known Activations