© 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. 15721
    Prev
    Next
    INDEX
    Explanations

    your understanding or details

    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
     %[
    -0.08
    é¢ij次
    -0.08
     ragaz
    -0.07
     Gür
    -0.07
    alama
    -0.07
    raki
    -0.07
     halde
    -0.07
    irket
    -0.07
    ustos
    -0.07
     Ders
    -0.07
    POSITIVE LOGITS
     Ä°mpar
    0.10
     geliÅŁ
    0.09
     hatır
    0.08
     kurtar
    0.08
    ÂŃi
    0.07
     önlem
    0.07
     uydu
    0.07
     embod
    0.07
    \OptionsResolver
    0.07
    SetValue
    0.07
    Activations Density 1.933%

    No Known Activations