© 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. 57733
    Prev
    Next
    INDEX
    Explanations

    world and globe scope

    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
     continental
    -0.17
     Continental
    -0.16
     continent
    -0.14
     Continent
    -0.13
    continental
    -0.11
    continent
    -0.11
     continents
    -0.09
     Kirk
    -0.09
     Oaks
    -0.09
    ichick
    -0.09
    POSITIVE LOGITS
     world
    0.39
     globe
    0.27
    ä¸ĸçķĮ
    0.26
    world
    0.26
     mundo
    0.24
     planet
    0.20
     wereld
    0.20
    -world
    0.20
     monde
    0.20
     миÑĢе
    0.19
    Activations Density 0.103%

    No Known Activations