© 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. 4458
    Prev
    Next
    INDEX
    Explanations

    brought out, as much, copy ng

    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
    ¶Į
    -0.08
    .UnitTesting
    -0.08
    sdk
    -0.07
    лиÑĪком
    -0.07
    xing
    -0.07
    ĥ½
    -0.07
    _customize
    -0.07
    ránÃŃ
    -0.07
    ¨ë¶Ģ
    -0.06
     -*
    -0.06
    POSITIVE LOGITS
     VÅ¡ech
    0.08
    yleft
    0.07
    :UITableView
    0.07
     Buccane
    0.07
    &&&&
    0.06
    ebek
    0.06
     huz
    0.06
     wiÄĻc
    0.06
    вок
    0.06
     بÙĪابة
    0.06
    Activations Density 0.027%

    No Known Activations