© 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. 36771
    Prev
    Next
    INDEX
    Explanations

    sensors and cameras

    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
     unmanned
    -0.13
    .Automation
    -0.11
    å¼ĭ
    -0.11
    747
    -0.11
    OMET
    -0.10
     blot
    -0.10
    Automation
    -0.09
     automated
    -0.09
     Maher
    -0.09
    _DEVICES
    -0.09
    POSITIVE LOGITS
     vision
    0.17
     Vision
    0.14
     sensor
    0.14
     sensors
    0.13
     Localization
    0.13
     software
    0.12
     perception
    0.12
     Li
    0.12
     obstacle
    0.12
     navigation
    0.12
    Activations Density 0.047%

    No Known Activations