© 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. 338
    Prev
    Next
    INDEX
    Explanations

    preventive or prevention of

    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
    imbus
    -0.10
    gor
    -0.09
    ÏĨο
    -0.09
    cro
    -0.09
    swick
    -0.09
     Tud
    -0.09
    cth
    -0.08
    JK
    -0.08
    atum
    -0.08
     incidental
    -0.08
    POSITIVE LOGITS
    atives
    0.16
    ions
    0.15
    /mit
    0.15
    atively
    0.15
    ative
    0.14
    æݪæĸ½
    0.14
    ively
    0.13
    itive
    0.13
    ive
    0.13
     measures
    0.12
    Activations Density 0.023%

    No Known Activations