© 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. 15801
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions like while

    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
    ohl
    -0.10
    ode
    -0.09
    eru
    -0.08
    é¢ij次
    -0.08
     Commons
    -0.08
    iku
    -0.08
    ltk
    -0.08
     Ùħرات
    -0.08
     tslint
    -0.08
    :maj
    -0.08
    POSITIVE LOGITS
    while
    0.15
     while
    0.15
    ï¼ĮèĢĮ
    0.14
     whereas
    0.13
     mentre
    0.12
     à¤ľà¤¬à¤ķ
    0.12
     mientras
    0.11
     èĢĮ
    0.11
     iar
    0.10
     enquanto
    0.10
    Activations Density 0.043%

    No Known Activations