© 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. 34484
    Prev
    Next
    INDEX
    Explanations

    its largest city

    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
     Commonwealth
    -0.10
     Weld
    -0.10
     Civ
    -0.10
     GOODMAN
    -0.10
     hus
    -0.09
    ÃĹ\n\n
    -0.09
     sticker
    -0.09
     district
    -0.09
     ç§
    -0.09
    YG
    -0.09
    POSITIVE LOGITS
     NJ
    0.43
     Jersey
    0.42
    NJ
    0.38
     Rutgers
    0.34
     nj
    0.34
     Bergen
    0.31
     Newark
    0.27
    nj
    0.27
     jersey
    0.27
    Jer
    0.25
    Activations Density 0.056%

    No Known Activations