© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25
    Prev
    Next
    INDEX
    Explanations

    love forms, gan, drip tape

    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
    UNUSED
    -0.08
    ̣
    -0.08
    ̧
    -0.08
     adipiscing
    -0.08
    =$('#
    -0.08
    :animated
    -0.08
    adiens
    -0.07
    .vertx
    -0.07
    berra
    -0.07
    åıĬåħ¶
    -0.07
    POSITIVE LOGITS
     fore
    0.08
    женÑĮ
    0.07
    åª
    0.07
    .
    0.07
    ï¼ģï¼ģ\n\n
    0.07
    ¹Ħ
    0.07
     democr
    0.07
    omore
    0.07
     succession
    0.07
     Coastal
    0.07
    Activations Density 0.033%

    No Known Activations