© 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. 28293
    Prev
    Next
    INDEX
    Explanations

    devices and platforms

    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
     mobile
    -0.25
     smartphones
    -0.24
     smartphone
    -0.24
    æīĭæľº
    -0.22
     Smartphone
    -0.22
    /mobile
    -0.21
     cellphone
    -0.21
     Mobile
    -0.21
    -mobile
    -0.19
    Mobile
    -0.19
    POSITIVE LOGITS
     tablet
    0.18
     desktop
    0.15
     tablets
    0.15
    TV
    0.13
    tablet
    0.13
     Tablet
    0.13
    PC
    0.13
     PC
    0.13
     Wear
    0.11
     TV
    0.11
    Activations Density 0.059%

    No Known Activations