© 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. 53876
    Prev
    Next
    INDEX
    Explanations

    SUV or crossover models

    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
     Vintage
    -0.11
     Automotive
    -0.10
     Ferrari
    -0.10
     Corvette
    -0.10
     automotive
    -0.10
     Volkswagen
    -0.10
    apiro
    -0.09
     Chevrolet
    -0.09
     Chrysler
    -0.09
     kt
    -0.09
    POSITIVE LOGITS
     crossover
    0.25
     SUV
    0.24
    rossover
    0.19
     CROSS
    0.17
     utility
    0.16
     hatch
    0.16
    UV
    0.16
     sport
    0.16
     Cross
    0.16
     Utility
    0.15
    Activations Density 0.053%

    No Known Activations