© 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. 61519
    Prev
    Next
    INDEX
    Explanations

    create new Next.js application

    np_acts-logits-general · gemini-2.5-flash-lite

    instructions for creating or initializing software applications or projects.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31

    instructional text describing how to create and set up a new software application.

    oai_token-act-pair · claude-4-5-haikuTriggered by @yooniel31
    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
    haps
    -0.11
     Werner
    -0.10
    à¹ģà¸Ļ
    -0.10
    763
    -0.09
    ô
    -0.09
     Tud
    -0.09
    yne
    -0.09
     bef
    -0.09
     Fre
    -0.09
    241
    -0.09
    POSITIVE LOGITS
     automatically
    0.12
     ready
    0.12
     automáticamente
    0.11
     draft
    0.11
     files
    0.10
     READY
    0.10
     èĩªåĬ¨çĶŁæĪIJ
    0.10
     default
    0.10
     folder
    0.10
    é»ĺ认
    0.10
    Activations Density 0.034%

    No Known Activations