© 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. 46412
    Prev
    Next
    INDEX
    Explanations

    safety protocols activated

    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
     Schiff
    -0.09
    022
    -0.09
     Cer
    -0.09
     Lambert
    -0.09
     Carlton
    -0.09
    ONGO
    -0.09
    plotlib
    -0.09
    atto
    -0.08
     McCorm
    -0.08
     indeb
    -0.08
    POSITIVE LOGITS
     activated
    0.28
     activation
    0.26
    activation
    0.20
    activated
    0.20
     Activation
    0.20
    Activated
    0.19
     active
    0.19
     fired
    0.19
     triggered
    0.18
     kicked
    0.18
    Activations Density 0.100%

    No Known Activations