© 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. 57696
    Prev
    Next
    INDEX
    Explanations

    knights and castles

    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
     bergen
    -0.11
     dign
    -0.10
     Dion
    -0.10
    åįļ士
    -0.09
    appy
    -0.09
     Civ
    -0.09
     Prometheus
    -0.09
     civilian
    -0.09
     Petty
    -0.09
     knife
    -0.09
    POSITIVE LOGITS
     knight
    0.32
     Knight
    0.29
     knights
    0.25
    Knight
    0.24
     Knights
    0.22
     tournament
    0.18
     tournaments
    0.18
     Sir
    0.18
    éªij
    0.17
     ÑĢÑĭ
    0.17
    Activations Density 0.071%

    No Known Activations