© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29818
    Prev
    Next
    INDEX
    Explanations

    champion of Pokemon

    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
     Wins
    -0.10
     championships
    -0.10
    ellow
    -0.10
     Championships
    -0.09
     wins
    -0.09
    -motion
    -0.09
    cores
    -0.09
    roy
    -0.09
    òa
    -0.09
    -space
    -0.09
    POSITIVE LOGITS
    SHIP
    0.15
    -status
    0.15
    ships
    0.15
    ship
    0.14
     status
    0.13
    hip
    0.13
    Ship
    0.12
    -cal
    0.11
    ess
    0.11
    cy
    0.11
    Activations Density 0.047%

    No Known Activations