© 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. 63844
    Prev
    Next
    INDEX
    Explanations

    country is the biggest producer of

    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
    ĥ½
    -0.10
    à¹ĩà¸ĩ
    -0.09
    ¶Į
    -0.09
    ³ç´°
    -0.09
    ¦æĥħ
    -0.09
    angen
    -0.08
    á»ĩu
    -0.08
    OfClass
    -0.08
    rve
    -0.08
    ometr
    -0.08
    POSITIVE LOGITS
     least
    0.11
     whose
    0.10
    least
    0.10
    (s
    0.09
    _BOTH
    0.09
     BOTH
    0.09
     meisten
    0.09
     ê°Ģìŀ¥
    0.09
     MOST
    0.09
     majority
    0.09
    Activations Density 0.287%

    No Known Activations