© 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. 52137
    Prev
    Next
    INDEX
    Explanations

    publishing in a newsletter or topic

    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
    .IsNullOr
    -0.09
     Tradable
    -0.09
    надлеж
    -0.09
    çĽijåIJ¬é¡µéĿ¢
    -0.09
    icari
    -0.09
    FileVersion
    -0.08
     ëħĦëıĦë³Ħ
    -0.08
    coe
    -0.08
    /***/
    -0.08
    Ìĥ
    -0.08
    POSITIVE LOGITS
     slee
    0.08
     Respect
    0.08
    oves
    0.08
    ABOUT
    0.08
    Notifier
    0.08
    .Net
    0.08
     Mate
    0.08
    divider
    0.08
    ảo
    0.07
    aison
    0.07
    Activations Density 0.471%

    No Known Activations