© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53830
    Prev
    Next
    INDEX
    Explanations

    University of California Berkeley

    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
     consum
    -0.12
     Consum
    -0.11
    realm
    -0.09
    ilot
    -0.09
    Telegram
    -0.09
     Baz
    -0.09
     Chips
    -0.09
    .nih
    -0.09
     Leaf
    -0.09
     Aleppo
    -0.09
    POSITIVE LOGITS
     Brewer
    0.14
     distributed
    0.12
     consistency
    0.12
     Cons
    0.12
     fault
    0.12
     liv
    0.12
    quals
    0.12
     systems
    0.11
     CAP
    0.11
     oblivious
    0.11
    Activations Density 0.064%

    No Known Activations