© 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. 56538
    Prev
    Next
    INDEX
    Explanations

    protecting and protective actions

    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
    102
    -0.10
     escape
    -0.09
    /ï¼ı
    -0.09
    318
    -0.09
     tamb
    -0.09
     escaping
    -0.09
    ured
    -0.09
     resistance
    -0.09
     countered
    -0.09
     escaped
    -0.09
    POSITIVE LOGITS
     protect
    0.48
    protect
    0.43
     protective
    0.42
     protection
    0.42
    ä¿ĿæĬ¤
    0.42
    Protect
    0.39
     protecting
    0.39
     protector
    0.38
     Protect
    0.38
     Protective
    0.36
    Activations Density 0.088%

    No Known Activations