© 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. 31249
    Prev
    Next
    INDEX
    Explanations

    I want to

    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
    292
    -0.10
     Kral
    -0.09
    adge
    -0.09
    illet
    -0.09
    /to
    -0.08
    vox
    -0.08
     stub
    -0.08
    /*č\n
    -0.08
    à¹ĥà¸Ķ
    -0.08
    /or
    -0.08
    POSITIVE LOGITS
    çļĦæĺ¯
    0.15
     savoir
    0.15
     know
    0.14
     rằng
    0.14
    оÑģÑĮ
    0.13
     wissen
    0.13
    çŁ¥éģĵ
    0.12
    Know
    0.11
     Know
    0.10
     hear
    0.10
    Activations Density 0.082%

    No Known Activations