© 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. 56944
    Prev
    Next
    INDEX
    Explanations

    Palace, government, royal seat

    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
     Duchess
    -0.10
     polarity
    -0.10
     Cov
    -0.10
     Border
    -0.09
     oasis
    -0.09
     prio
    -0.09
     Differential
    -0.09
     Parliamentary
    -0.08
    Border
    -0.08
    province
    -0.08
    POSITIVE LOGITS
     palace
    0.31
     Palace
    0.31
     pal
    0.27
    宫
    0.22
    pal
    0.22
     seat
    0.21
    å®®
    0.21
    Pal
    0.21
     Pal
    0.20
     Buckingham
    0.19
    Activations Density 0.090%

    No Known Activations