© 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. 58634
    Prev
    Next
    INDEX
    Explanations

    more than

    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
     more
    -0.12
    753
    -0.10
    æĽ´åĬł
    -0.09
     более
    -0.09
    zag
    -0.09
    mour
    -0.09
     daha
    -0.09
    ÛĮس
    -0.09
     Kerry
    -0.09
    DTD
    -0.09
    POSITIVE LOGITS
     than
    0.18
     tarde
    0.17
     niż
    0.12
    -than
    0.12
    ieurs
    0.12
    ieur
    0.12
    Than
    0.11
     вÑģего
    0.11
    /new
    0.11
    _vert
    0.11
    Activations Density 0.030%

    No Known Activations