© 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. 44057
    Prev
    Next
    INDEX
    Explanations

    target and kill cancer

    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
     Hide
    -0.10
    viso
    -0.10
     Chic
    -0.10
     ters
    -0.10
    è¤
    -0.10
     objc
    -0.09
    DOB
    -0.09
    Hide
    -0.09
    ãĥ¼
    -0.09
     Jad
    -0.09
    POSITIVE LOGITS
     kill
    0.25
     killing
    0.23
     kills
    0.22
    æĿĢ
    0.20
     death
    0.20
    kill
    0.19
     Kill
    0.19
     irre
    0.18
    kills
    0.18
     killed
    0.18
    Activations Density 0.043%

    No Known Activations