© 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. 13770
    Prev
    Next
    INDEX
    Explanations

    devices and communication

    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
     iPhones
    -0.15
     Smartphone
    -0.13
     iphone
    -0.13
    iPad
    -0.12
     iPhone
    -0.12
     ipad
    -0.12
    iPhone
    -0.11
     cellphone
    -0.11
     iPad
    -0.10
     iP
    -0.10
    POSITIVE LOGITS
     devices
    0.47
     device
    0.46
    设å¤ĩ
    0.35
    device
    0.34
     Devices
    0.34
    devices
    0.32
     Device
    0.31
    .device
    0.29
     zaÅĻÃŃzenÃŃ
    0.28
    Device
    0.27
    Activations Density 0.157%

    No Known Activations