© 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. 63290
    Prev
    Next
    INDEX
    Explanations

    instead of or not

    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
    ayan
    -0.09
    ulk
    -0.08
     pret
    -0.08
    552
    -0.08
     Hin
    -0.08
    hud
    -0.08
     Ire
    -0.08
     Fitzgerald
    -0.08
    uis
    -0.08
    :
    -0.08
    POSITIVE LOGITS
     plain
    0.13
     separate
    0.11
     individual
    0.10
    缴æİ¥
    0.10
     ÐĴики
    0.10
    precated
    0.10
    DRV
    0.10
    /raw
    0.10
    éĿł
    0.10
     just
    0.10
    Activations Density 0.054%

    No Known Activations