© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39004
    Prev
    Next
    INDEX
    Explanations

    to enhance or protect

    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
    uese
    -0.12
    IfNeeded
    -0.09
    ,");\n
    -0.09
    stp
    -0.09
    uxtap
    -0.09
     Morse
    -0.08
    .Abstractions
    -0.08
     Lange
    -0.08
    512
    -0.08
    ams
    -0.08
    POSITIVE LOGITS
     purposes
    0.14
    izzare
    0.13
    ваÑĤÑĮ
    0.12
    иÑĤÑĮ
    0.11
     Wyn
    0.11
    zyÄĩ
    0.11
    ÑĩиÑĤÑĮ
    0.10
    indre
    0.10
    ниÑĤÑĮ
    0.10
    кÑĥваÑĤи
    0.10
    Activations Density 0.089%

    No Known Activations