© 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. 15516
    Prev
    Next
    INDEX
    Explanations

    benchmark and threshold

    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
    lÃŃ
    -0.10
    iline
    -0.10
    atab
    -0.09
    ruba
    -0.09
    vig
    -0.09
    plotlib
    -0.09
    aro
    -0.09
    ENA
    -0.09
    ÐķС
    -0.09
    ıt
    -0.09
    POSITIVE LOGITS
    ing
    0.27
    ed
    0.23
    eting
    0.15
    ry
    0.12
    ize
    0.12
    ers
    0.11
    ries
    0.11
    eer
    0.11
    sg
    0.11
    -setting
    0.11
    Activations Density 0.082%

    No Known Activations