© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    country names

    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
     Bulgarian
    -0.12
    airobi
    -0.11
     Romanian
    -0.11
     Nicar
    -0.10
     Tas
    -0.10
    æµ·å¤ĸ
    -0.10
     Ethiopian
    -0.10
     madrid
    -0.10
     Yugosl
    -0.10
     Eston
    -0.09
    POSITIVE LOGITS
     USA
    0.24
     Canada
    0.23
     France
    0.22
     Japan
    0.20
     United
    0.20
     China
    0.20
     Germany
    0.19
     Australia
    0.18
     Russia
    0.18
     England
    0.18
    Activations Density 0.192%

    No Known Activations