© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    internationally beyond abroad

    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
    vard
    -0.10
    mers
    -0.09
    æĢ
    -0.09
     mainland
    -0.09
    anik
    -0.09
     domestic
    -0.08
    alez
    -0.08
     baÅŁk
    -0.08
     domestically
    -0.08
    aken
    -0.08
    POSITIVE LOGITS
     beyond
    0.31
     abroad
    0.25
     Beyond
    0.21
    Beyond
    0.20
     elsewhere
    0.20
    else
    0.18
    eyond
    0.15
    Else
    0.15
     bey
    0.14
     indeed
    0.14
    Activations Density 0.055%

    No Known Activations