© 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. 10611
    Prev
    Next
    INDEX
    Explanations

    no matter how dangerous

    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
    Negative Logits
    <|begin_of_text|>
    -0.10
     Cous
    -0.09
    figcaption
    -0.08
    ¶Į
    -0.08
    aeda
    -0.08
    ä½
    -0.08
    collapsed
    -0.08
     plaint
    -0.08
     Busty
    -0.08
    .OP
    -0.08
    POSITIVE LOGITS
     âĢŀ
    0.10
    hint
    0.09
     solid
    0.09
     fetisch
    0.08
     real
    0.08
     («
    0.08
     fuck
    0.08
     crist
    0.08
     «
    0.08
     kaf
    0.08
    Activations Density 0.215%

    No Known Activations