© 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. 46630
    Prev
    Next
    INDEX
    Explanations

    personal meaning and vision

    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
     underst
    -0.12
    nes
    -0.10
    iman
    -0.09
    ï¼Ŀ
    -0.09
    kla
    -0.09
     mindful
    -0.09
    NES
    -0.09
     wrap
    -0.09
     Lesson
    -0.09
     memor
    -0.09
    POSITIVE LOGITS
     journal
    0.23
     intros
    0.17
     reflect
    0.17
     reflection
    0.16
     Journal
    0.16
    Reflect
    0.15
    journal
    0.15
     journals
    0.14
     asking
    0.14
     Reflection
    0.14
    Activations Density 0.078%

    No Known Activations