© 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. 49132
    Prev
    Next
    INDEX
    Explanations

    parking and stopping cars

    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
    aval
    -0.10
     plo
    -0.10
    ipel
    -0.09
    -cart
    -0.09
     pel
    -0.09
    obus
    -0.09
    ï¼¾
    -0.09
    ritten
    -0.09
     Kraft
    -0.09
    à¸Ļà¸Ļ
    -0.09
    POSITIVE LOGITS
     parking
    0.25
     Parking
    0.21
     car
    0.20
     trunk
    0.19
    Parking
    0.18
    park
    0.18
     driver
    0.16
     park
    0.16
     hon
    0.16
     passenger
    0.15
    Activations Density 0.047%

    No Known Activations