© 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. 18332
    Prev
    Next
    INDEX
    Explanations

    using by via

    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
    ighton
    -0.09
    aggi
    -0.09
    xmax
    -0.08
     cob
    -0.08
     indirect
    -0.08
    uma
    -0.08
     dormant
    -0.08
     Bowen
    -0.08
    ëĮĢìĿĺ
    -0.08
     Zak
    -0.08
    POSITIVE LOGITS
     using
    0.21
     bằng
    0.20
    using
    0.17
     by
    0.17
     menggunakan
    0.16
    使çĶ¨
    0.16
     pomocÃŃ
    0.15
     via
    0.14
     使çĶ¨
    0.14
     помоÑīÑĮÑİ
    0.13
    Activations Density 0.034%

    No Known Activations