© 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. 17912
    Prev
    Next
    INDEX
    Explanations

    a rate or faster rate

    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
    _trampoline
    -0.09
    adder
    -0.09
    Leap
    -0.09
    alties
    -0.08
    дÑı
    -0.08
     collusion
    -0.08
     Rush
    -0.08
    prene
    -0.08
    rv
    -0.08
    rij
    -0.08
    POSITIVE LOGITS
     rate
    0.75
     Rate
    0.61
     rates
    0.57
    rate
    0.55
    Rate
    0.54
    _rate
    0.49
     RATE
    0.48
     Rates
    0.46
    .rate
    0.45
    -rate
    0.44
    Activations Density 0.114%

    No Known Activations