© 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. 23618
    Prev
    Next
    INDEX
    Explanations

    ErHuan West Rode X

    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
     ë¨
    -0.09
    urette
    -0.09
     ë¸
    -0.09
    -bars
    -0.08
    oldt
    -0.08
     åıĮ线
    -0.08
    ï¼Ŀï¼Ŀ
    -0.08
    abeth
    -0.08
     Ä°mpar
    -0.08
    iface
    -0.08
    POSITIVE LOGITS
    most
    0.09
     Gilles
    0.08
    iyah
    0.08
    ิà¹Ģวà¸ĵ
    0.08
    istol
    0.08
    wise
    0.08
    .obtain
    0.08
    uration
    0.08
    δÏĮν
    0.08
    ÑĢаниÑĨ
    0.08
    Activations Density 0.138%

    No Known Activations