© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37526
    Prev
    Next
    INDEX
    Explanations

    Guangdong, Guangxi, Guanghua

    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
    'gc
    -0.11
    enty
    -0.10
     ded
    -0.09
     hostel
    -0.09
    Flip
    -0.09
     Webcam
    -0.09
     Flip
    -0.09
    etter
    -0.09
    iser
    -0.09
    ks
    -0.09
    POSITIVE LOGITS
    anteed
    0.15
     gu
    0.14
    ierrez
    0.13
     Gu
    0.12
    Gu
    0.12
    .Gson
    0.12
    dong
    0.11
     GU
    0.11
    zhou
    0.10
    enheim
    0.10
    Activations Density 0.048%

    No Known Activations