© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    sea turtles gliding; they are; its size

    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
     nests
    -0.11
    riba
    -0.10
     Fate
    -0.10
     Benchmark
    -0.10
     доÑĢож
    -0.09
    ossa
    -0.09
    elsen
    -0.09
    .spi
    -0.09
     Expedition
    -0.09
    reib
    -0.09
    POSITIVE LOGITS
     migration
    0.19
     Migration
    0.15
    migration
    0.15
    Migration
    0.14
     migrations
    0.14
     migr
    0.14
     mig
    0.14
     мÑĸг
    0.12
     predictable
    0.12
     season
    0.12
    Activations Density 0.038%

    No Known Activations