© 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. 29131
    Prev
    Next
    INDEX
    Explanations

    Pearl Harbor

    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
     helicopter
    -0.10
     Pik
    -0.09
    è¡Ľ
    -0.09
    Invoker
    -0.09
    inders
    -0.09
    åį«
    -0.09
    illery
    -0.09
    ortex
    -0.09
     ()->
    -0.09
     Soldier
    -0.09
    POSITIVE LOGITS
     Pearl
    0.34
    Pear
    0.29
     pearl
    0.25
     Pear
    0.21
    pear
    0.21
    PEAR
    0.20
     pear
    0.19
    çıį
    0.18
     pearls
    0.18
     attack
    0.17
    Activations Density 0.017%

    No Known Activations