© 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. 4742
    Prev
    Next
    INDEX
    Explanations

    router router, file named

    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
     vex
    -0.09
     Lau
    -0.09
     Associates
    -0.09
    aac
    -0.09
     infer
    -0.08
    _CTL
    -0.08
    ongyang
    -0.08
    rij
    -0.08
     Burl
    -0.08
     Tul
    -0.08
    POSITIVE LOGITS
    printStats
    0.11
    oola
    0.10
    isContained
    0.09
    ette
    0.09
    -with
    0.09
     itself
    0.09
    èĩªèº«
    0.09
     Bair
    0.09
     à¸ģรà¸ģ
    0.09
    pare
    0.08
    Activations Density 0.344%

    No Known Activations