© 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. 1460
    Prev
    Next
    INDEX
    Explanations

    what about today

    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
     BITTE
    -0.09
    ï¿
    -0.09
     çµIJ
    -0.08
    roud
    -0.07
    otal
    -0.07
    ÄĤ
    -0.07
    ãĤ±ãĥ¼ãĤ¹
    -0.07
     HttpStatusCode
    -0.07
    _Api
    -0.07
    antanamo
    -0.07
    POSITIVE LOGITS
     indeed
    0.12
    ï
    0.09
     ấy
    0.09
    .SuspendLayout
    0.09
    ฯ
    0.09
    çĿ
    0.08
    Latch
    0.08
    .assets
    0.08
     etc
    0.08
     meas
    0.08
    Activations Density 0.451%

    No Known Activations