© 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. 41507
    Prev
    Next
    INDEX
    Explanations

    data breach or leak

    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
    JsonValue
    -0.10
    fea
    -0.10
     dismant
    -0.10
    utzer
    -0.10
    Unnamed
    -0.10
     anonymous
    -0.09
    OTES
    -0.09
     Khoa
    -0.09
     desper
    -0.09
    çĨ
    -0.08
    POSITIVE LOGITS
    æ³
    0.22
     exposure
    0.17
    æ´
    0.17
     leak
    0.17
     lá»Ļ
    0.16
     bree
    0.16
     comprom
    0.16
     release
    0.15
     compromise
    0.15
     exposed
    0.15
    Activations Density 0.073%

    No Known Activations