© 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. 49124
    Prev
    Next
    INDEX
    Explanations

    Week 11 NFC games

    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
     Tournament
    -0.12
     Championships
    -0.10
     showdown
    -0.10
     tournaments
    -0.10
    SSERT
    -0.10
    ÐIJÑĢÑħÑĸв
    -0.09
    tournament
    -0.09
     Morning
    -0.09
     mornings
    -0.09
    PKG
    -0.09
    POSITIVE LOGITS
     match
    0.22
     matches
    0.19
    match
    0.18
     games
    0.18
     game
    0.17
     fixture
    0.17
     friendly
    0.17
    -match
    0.15
     Friendly
    0.15
     away
    0.14
    Activations Density 0.076%

    No Known Activations