© 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. 13184
    Prev
    Next
    INDEX
    Explanations

    common name, talented young, best starting

    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
     Wimbledon
    -0.13
     ump
    -0.13
     Premiership
    -0.11
    itler
    -0.10
     Rugby
    -0.10
    urovision
    -0.10
     Warwick
    -0.10
     Cristiano
    -0.09
     catcher
    -0.09
    ombat
    -0.09
    POSITIVE LOGITS
     player
    0.27
     players
    0.26
     club
    0.20
     transfer
    0.20
     football
    0.19
     goal
    0.18
     Player
    0.18
     fans
    0.18
     team
    0.18
     Transfer
    0.18
    Activations Density 0.164%

    No Known Activations