© 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. 33003
    Prev
    Next
    INDEX
    Explanations

    should be banned

    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
    aber
    -0.09
    inel
    -0.09
    iage
    -0.08
    анÑĥ
    -0.08
     cur
    -0.08
    antis
    -0.08
    cheduler
    -0.08
    oker
    -0.08
    dete
    -0.08
     breakthrough
    -0.08
    POSITIVE LOGITS
     should
    0.15
    åºĶ该
    0.12
    should
    0.12
     Should
    0.11
     personel
    0.11
     shouldn
    0.11
     employees
    0.11
     Ade
    0.10
     workers
    0.10
    .should
    0.10
    Activations Density 0.012%

    No Known Activations