© 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. 27084
    Prev
    Next
    INDEX
    Explanations

    accepting and making

    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
    achuset
    -0.11
    buz
    -0.09
     unst
    -0.09
    kyt
    -0.09
     Incontri
    -0.09
    avian
    -0.09
     ach
    -0.09
     Fit
    -0.08
    awn
    -0.08
     Solid
    -0.08
    POSITIVE LOGITS
    embr
    0.29
     embrace
    0.26
     embraced
    0.23
     embracing
    0.21
     accept
    0.19
    accept
    0.19
     acceptance
    0.19
     embraces
    0.18
     Accept
    0.18
     welcome
    0.17
    Activations Density 0.113%

    No Known Activations