© 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. 3605
    Prev
    Next
    INDEX
    Explanations

    Antarctica and Antarctic

    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
    à¹ĥà¸Ļส
    -0.10
    Mexico
    -0.09
     Graz
    -0.09
    deer
    -0.09
     Mexico
    -0.09
    彡
    -0.08
    ï¼ľ
    -0.08
     Loren
    -0.08
     supers
    -0.08
     Isle
    -0.08
    POSITIVE LOGITS
     ice
    0.21
     Antarctica
    0.20
    Ant
    0.19
     Antarctic
    0.19
    antar
    0.19
     polar
    0.18
     Antar
    0.17
     Ice
    0.17
     Ross
    0.16
    ANT
    0.16
    Activations Density 0.013%

    No Known Activations