© 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. 22768
    Prev
    Next
    INDEX
    Explanations

    roads, lanes and their extent

    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
     highways
    -0.12
     interstate
    -0.12
     rear
    -0.12
     highway
    -0.11
     roadway
    -0.11
     roadside
    -0.11
     freeway
    -0.10
     Highway
    -0.10
     paved
    -0.10
     Interstate
    -0.10
    POSITIVE LOGITS
     leading
    0.18
    ides
    0.14
     Leading
    0.14
    leading
    0.14
     widths
    0.13
    Leading
    0.12
     ÑĪиÑĢ
    0.12
     width
    0.12
    width
    0.12
     Width
    0.12
    Activations Density 0.071%

    No Known Activations