© 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. 9384
    Prev
    Next
    INDEX
    Explanations

    dangerous behaviors

    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
    ÑĢаб
    -0.10
    747
    -0.09
    ê·¼
    -0.09
    ugu
    -0.09
    éĮ
    -0.09
    lap
    -0.09
    subst
    -0.09
     ovar
    -0.09
    ukkit
    -0.09
     dislikes
    -0.09
    POSITIVE LOGITS
     lies
    0.15
     interrupt
    0.15
     lie
    0.14
    rud
    0.13
     late
    0.13
    ossip
    0.12
     litter
    0.12
    Lie
    0.12
    Cli
    0.12
     bel
    0.12
    Activations Density 0.176%

    No Known Activations