© 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. 39698
    Prev
    Next
    INDEX
    Explanations

    malicious intent or intended harm

    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
    unar
    -0.09
     odp
    -0.09
    idel
    -0.09
     pronounce
    -0.09
    kea
    -0.09
    ¥¤
    -0.09
    /umd
    -0.08
    layan
    -0.08
    .newBuilder
    -0.08
    arine
    -0.08
    POSITIVE LOGITS
     intent
    0.20
     intention
    0.19
    Intent
    0.18
     intended
    0.17
    intent
    0.17
     context
    0.16
     meant
    0.16
     Intent
    0.16
     intentions
    0.15
     delivery
    0.14
    Activations Density 0.152%

    No Known Activations