© 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. 2390
    Prev
    Next
    INDEX
    Explanations

    connecting paired attributes

    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
     various
    -0.14
     Various
    -0.12
    893
    -0.10
    Various
    -0.09
    adir
    -0.09
    ;element
    -0.09
     likes
    -0.09
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.09
    _notifier
    -0.08
    âĦĸâĦĸ
    -0.08
    POSITIVE LOGITS
    /or
    0.19
    /OR
    0.11
    .or
    0.10
    /of
    0.10
     emph
    0.09
     characteristics
    0.09
     battleground
    0.09
    OTA
    0.09
    colo
    0.09
    ubb
    0.08
    Activations Density 0.086%

    No Known Activations