© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 10573
    Prev
    Next
    INDEX
    Explanations

    most or best of a category

    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
    Negative Logits
    hpp
    -0.09
    lass
    -0.09
    ipp
    -0.09
    emann
    -0.09
    _exc
    -0.09
    pio
    -0.08
    _Matrix
    -0.08
    serrat
    -0.08
    itty
    -0.08
    shouldBe
    -0.08
    POSITIVE LOGITS
     ever
    0.21
     possible
    0.17
    ä¹ĭä¸Ģ
    0.16
     ÙħÙħÚ©ÙĨ
    0.16
     posible
    0.16
     overall
    0.15
     available
    0.15
    possible
    0.13
     yet
    0.13
     possÃŃvel
    0.13
    Activations Density 0.190%

    No Known Activations