© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    scrapping, deleting, destroying

    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
    èĦ±
    -0.10
    Crud
    -0.09
     severed
    -0.09
    æĿ¾
    -0.09
    éĢĥ
    -0.09
    Dirty
    -0.09
    Intialized
    -0.09
     Ending
    -0.09
     slamming
    -0.09
    ober
    -0.09
    POSITIVE LOGITS
     destruction
    0.35
     destroy
    0.32
     destroyed
    0.31
    .destroy
    0.29
     delete
    0.28
     Destroy
    0.28
    åĪłéĻ¤
    0.28
    destroy
    0.27
     destroying
    0.27
     Destruction
    0.27
    Activations Density 0.128%

    No Known Activations