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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38734
    Prev
    Next
    INDEX
    Explanations

    mainly/primarily

    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
     Moder
    -0.09
    oe
    -0.09
     Gund
    -0.09
     ab
    -0.09
     Lowest
    -0.08
    ella
    -0.08
    inge
    -0.08
    ulls
    -0.08
     lust
    -0.08
     Pow
    -0.08
    POSITIVE LOGITS
     mostly
    0.41
    主è¦ģ
    0.35
    mostly
    0.35
     mainly
    0.33
     оÑģновном
    0.29
     majority
    0.28
    main
    0.28
     primarily
    0.27
     largely
    0.26
     chủ
    0.24
    Activations Density 0.322%

    No Known Activations