© 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. 23257
    Prev
    Next
    INDEX
    Explanations

    through a network

    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
    .scalablytyped
    -0.07
    .writeObject
    -0.06
     TMPro
    -0.06
     [](
    -0.06
     Blogs
    -0.06
     =>'
    -0.06
     threadIdx
    -0.06
     berlin
    -0.06
     fz
    -0.06
     VÅ¡ech
    -0.06
    POSITIVE LOGITS
    ¶Į
    0.10
     jadx
    0.08
    ĥ½
    0.08
    οÏģειο
    0.07
    .Formatter
    0.07
    elige
    0.07
    CustomLabel
    0.07
    .Dictionary
    0.07
     íĮĮìĿ¼ì²¨ë¶Ģ
    0.07
    tml
    0.06
    Activations Density 1.102%

    No Known Activations