© 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. 42480
    Prev
    Next
    INDEX
    Explanations

    widespread / global / entire

    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
     $('#'
    -0.10
     intertwined
    -0.09
     appropri
    -0.09
     dispens
    -0.09
    oler
    -0.09
     Overflow
    -0.09
     Glas
    -0.08
    sono
    -0.08
    ＿__
    -0.08
    ulin
    -0.08
    POSITIVE LOGITS
     wide
    0.32
     rá»Ļng
    0.30
     widespread
    0.30
    广
    0.29
    åºĥ
    0.29
    -wide
    0.28
     wider
    0.27
    wide
    0.26
     scope
    0.25
    廣
    0.25
    Activations Density 0.226%

    No Known Activations