© 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. 21407
    Prev
    Next
    INDEX
    Explanations

    discipline, dominance, desires, 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
    Not in Any Lists

    No Comments

    Negative Logits
    -bordered
    -0.11
     glBind
    -0.10
     bondage
    -0.10
    \tglBind
    -0.09
    .DataBind
    -0.09
    ideo
    -0.09
     bonds
    -0.09
    OMPI
    -0.09
    ·
    -0.09
    .setBounds
    -0.09
    POSITIVE LOGITS
    .ButterKnife
    0.12
    UNCH
    0.10
    angler
    0.10
    ë°
    0.09
    _RGBA
    0.09
    auce
    0.09
    .:.:.:.
    0.09
     gag
    0.08
    PTS
    0.08
    PropertyValue
    0.08
    Activations Density 0.122%

    No Known Activations