© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25326
    Prev
    Next
    INDEX
    Explanations

    Guard Gate, Iot, velocidad, puerta

    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
    άνÏĦα
    -0.07
    NewItem
    -0.07
    .Utility
    -0.07
    ıi
    -0.07
    .Transactional
    -0.07
     zug
    -0.07
    zı
    -0.07
    ê°¤
    -0.07
    .nr
    -0.07
    kf
    -0.07
    POSITIVE LOGITS
     Copp
    0.09
    (íģ¬ê¸°
    0.09
    ä½ľçĶ¨
    0.09
     VÅ¡ech
    0.08
    opoly
    0.07
     اÙĦکترÙĪÙĨ
    0.07
     mechanism
    0.07
    $MESS
    0.07
    eut
    0.07
     sperma
    0.07
    Activations Density 0.066%

    No Known Activations