© 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. 22791
    Prev
    Next
    INDEX
    Explanations

    arm and arms

    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
     toes
    -0.18
     toe
    -0.16
    èħ°
    -0.13
     feet
    -0.12
     Toe
    -0.11
     Feet
    -0.11
     fingert
    -0.11
     Nose
    -0.11
     forehead
    -0.10
     butto
    -0.10
    POSITIVE LOGITS
     arm
    0.64
     Arm
    0.49
     arms
    0.49
    Arm
    0.45
    arm
    0.43
     Arms
    0.41
    -arm
    0.39
    arms
    0.38
     ARM
    0.35
    _arm
    0.34
    Activations Density 0.075%

    No Known Activations