© 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. 18815
    Prev
    Next
    INDEX
    Explanations

    respecting personal boundaries and consent

    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
     UFO
    -0.10
     bypass
    -0.09
    awe
    -0.09
     sexes
    -0.09
    893
    -0.09
    604
    -0.09
    inou
    -0.09
     Sır
    -0.09
    lica
    -0.09
    strup
    -0.08
    POSITIVE LOGITS
     boundaries
    0.33
     boundary
    0.23
     comfort
    0.20
     limits
    0.20
     Bound
    0.19
     Boundary
    0.19
     wishes
    0.19
     consent
    0.19
     feelings
    0.18
    comfort
    0.16
    Activations Density 0.037%

    No Known Activations