© 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. 16022
    Prev
    Next
    INDEX
    Explanations

    Caribbean islands

    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
     McCl
    -0.11
     Bernardino
    -0.10
     Hawaiian
    -0.10
     Bentley
    -0.10
     McL
    -0.09
     Venice
    -0.09
     Braun
    -0.09
     Aless
    -0.09
     Autumn
    -0.09
     autumn
    -0.09
    POSITIVE LOGITS
     Caribbean
    0.26
    Montserrat
    0.26
     Gren
    0.25
     Barb
    0.24
     island
    0.23
     SVG
    0.23
    SVG
    0.22
     Turks
    0.22
     Tob
    0.21
    ibbean
    0.20
    Activations Density 0.033%

    No Known Activations