© 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. 55798
    Prev
    Next
    INDEX
    Explanations

    wide range or variety

    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
     plentiful
    -0.10
    ormsg
    -0.10
     several
    -0.10
    VAS
    -0.09
     Wander
    -0.09
    å¤ļå°ij
    -0.09
    .UnitTesting
    -0.09
    bruar
    -0.09
    åĩłä¸ª
    -0.09
    wm
    -0.09
    POSITIVE LOGITS
     wide
    0.68
     broad
    0.52
     ÑĪиÑĢок
    0.50
     Wide
    0.49
    Wide
    0.48
     widest
    0.48
    wide
    0.48
     wider
    0.46
     rá»Ļng
    0.44
     range
    0.42
    Activations Density 0.157%

    No Known Activations