© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18500
    Prev
    Next
    INDEX
    Explanations

    NAME_1: placeholders

    np_acts-logits-general · gemini-2.5-flash-lite

    jailbreak prompts or instructions attempting to manipulate AI model behavior.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     Unless
    -0.10
     forg
    -0.10
    eros
    -0.09
    หว
    -0.09
     unless
    -0.09
    obot
    -0.09
     homosexual
    -0.08
     Porno
    -0.08
     humble
    -0.08
    &
    -0.08
    POSITIVE LOGITS
     unre
    0.10
    SURE
    0.10
    ALLE
    0.09
     sure
    0.09
     freedom
    0.09
     Freedom
    0.09
    xea
    0.09
     инÑĦоÑĢма
    0.08
    å¾Ħ
    0.08
     absolute
    0.08
    Activations Density 0.045%

    No Known Activations