© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33521
    Prev
    Next
    INDEX
    Explanations

    jailbreak and boilerplate

    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
    OptionsMenu
    -0.11
    mast
    -0.09
     Interracial
    -0.08
    ipher
    -0.08
     hon
    -0.08
    rypton
    -0.08
    .createServer
    -0.08
    ixer
    -0.08
     Kou
    -0.08
    âķĹ
    -0.08
    POSITIVE LOGITS
    -style
    0.09
    298
    0.09
     Joey
    0.09
    KIT
    0.08
     whistle
    0.08
    iesen
    0.08
    ám
    0.08
     ngũ
    0.08
    ajs
    0.08
     Wil
    0.08
    Activations Density 0.242%

    No Known Activations