© 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. 53420
    Prev
    Next
    INDEX
    Explanations

    dismissive, disparaging, treat poorly

    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
    andes
    -0.09
    alim
    -0.09
     pon
    -0.09
    ampo
    -0.09
     нен
    -0.09
    æľ
    -0.09
    óc
    -0.09
     slander
    -0.08
    aeda
    -0.08
    voke
    -0.08
    POSITIVE LOGITS
     dismiss
    0.41
     dismissed
    0.35
     dismissal
    0.34
    dismiss
    0.34
    Dismiss
    0.33
     dismissing
    0.31
    -dismiss
    0.30
    .dismiss
    0.27
     patron
    0.26
     brush
    0.22
    Activations Density 0.085%

    No Known Activations