© 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. 32880
    Prev
    Next
    INDEX
    Explanations

    provide insight and benefits

    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
     поба
    -0.12
     unravel
    -0.09
     afin
    -0.09
    é§IJ
    -0.08
    ermal
    -0.08
    Sanders
    -0.08
     pimp
    -0.08
     Sanders
    -0.08
    .aspx
    -0.08
     Dolphin
    -0.08
    POSITIVE LOGITS
    æıIJä¾Ľ
    0.21
     providing
    0.20
     provide
    0.19
     cung
    0.17
     help
    0.17
     provides
    0.17
    Provide
    0.15
    provide
    0.14
     provided
    0.14
     act
    0.14
    Activations Density 0.189%

    No Known Activations