© 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. 55548
    Prev
    Next
    INDEX
    Explanations

    engage or engaged

    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
    879
    -0.10
     Tran
    -0.10
    Subset
    -0.09
    elter
    -0.09
    agna
    -0.08
    =rand
    -0.08
    827
    -0.08
     Lever
    -0.08
     Umb
    -0.08
     Strip
    -0.08
    POSITIVE LOGITS
     engage
    0.45
    engage
    0.43
     engaging
    0.42
     engaged
    0.42
     engages
    0.40
     engagement
    0.37
     Engagement
    0.33
     Eng
    0.33
    Eng
    0.32
    eng
    0.28
    Activations Density 0.217%

    No Known Activations