© 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. 28260
    Prev
    Next
    INDEX
    Explanations

    fun and enjoyable experiences

    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
    ëįĶëĭĪ
    -0.09
    827
    -0.09
    465
    -0.09
    женÑĮ
    -0.09
    824
    -0.08
    лаÑĩ
    -0.08
    diet
    -0.08
     Bite
    -0.08
    elize
    -0.08
     поба
    -0.08
    POSITIVE LOGITS
     fun
    0.53
     enjoyment
    0.46
     pleasure
    0.45
     enjoyable
    0.44
     enjoy
    0.41
     Enjoy
    0.40
    Enjoy
    0.39
    享
    0.39
     ple
    0.39
     enjoyed
    0.38
    Activations Density 0.193%

    No Known Activations