© 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. 20131
    Prev
    Next
    INDEX
    Explanations

    may keep secrets

    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
     Harr
    -0.10
     deactivated
    -0.09
    ''''
    -0.09
     subdued
    -0.09
    neutral
    -0.09
     unc
    -0.08
    ÃĹ\n\n
    -0.08
    ública
    -0.08
    EMPLARY
    -0.08
    надлеж
    -0.08
    POSITIVE LOGITS
     kept
    0.34
     secrets
    0.32
     secret
    0.32
    ç§ĺ
    0.31
     keeping
    0.30
     secrecy
    0.30
     hiding
    0.29
     keep
    0.28
     conce
    0.27
     Secrets
    0.27
    Activations Density 0.215%

    No Known Activations