© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 132
    Prev
    Next
    INDEX
    Explanations

    frontend and backend development

    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
     software
    -0.12
    software
    -0.12
    /software
    -0.10
    软件
    -0.10
    Software
    -0.10
     Websites
    -0.10
    rok
    -0.09
     Software
    -0.09
     ausp
    -0.09
    .Framework
    -0.09
    POSITIVE LOGITS
     backend
    0.14
    -backend
    0.13
    backend
    0.13
     animations
    0.12
    Backend
    0.12
    _backend
    0.12
     logic
    0.12
     animation
    0.11
     Backend
    0.11
     inner
    0.10
    Activations Density 0.083%

    No Known Activations