© 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. 34378
    Prev
    Next
    INDEX
    Explanations

    your web application

    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
    getRepository
    -0.10
     Opposition
    -0.09
    subpackage
    -0.09
    ible
    -0.09
     Reyn
    -0.09
    SEO
    -0.09
    /apache
    -0.08
    ounters
    -0.08
    /problems
    -0.08
    eus
    -0.08
    POSITIVE LOGITS
     applications
    0.23
     application
    0.20
    applications
    0.17
     developers
    0.17
     apps
    0.16
     app
    0.16
     Applications
    0.16
     Developers
    0.15
    application
    0.15
    åºĶçĶ¨
    0.14
    Activations Density 0.153%

    No Known Activations