© 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. 49953
    Prev
    Next
    INDEX
    Explanations

    facilitate communication in IoT

    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
    mpi
    -0.10
     WIFI
    -0.09
    _OC
    -0.09
     pcm
    -0.09
    robot
    -0.09
    लब
    -0.09
    umped
    -0.09
    _GPU
    -0.08
    æĿIJ
    -0.08
    unner
    -0.08
    POSITIVE LOGITS
    iot
    0.25
     IoT
    0.20
    Io
    0.20
     device
    0.19
     Device
    0.18
     Thing
    0.18
     MQTT
    0.15
     Industrial
    0.15
     gateway
    0.14
     Lo
    0.14
    Activations Density 0.051%

    No Known Activations