© 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. 22561
    Prev
    Next
    INDEX
    Explanations

    swallowing and dangerous

    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
    zi
    -0.12
    -âĢIJ
    -0.10
     èĴ
    -0.10
     Wand
    -0.09
    elda
    -0.09
    emente
    -0.09
     shr
    -0.09
    -out
    -0.09
    ãĥ
    -0.08
    ACHI
    -0.08
    POSITIVE LOGITS
     swallow
    0.29
     swallowing
    0.27
     swallowed
    0.27
     gulp
    0.20
     gag
    0.17
     Sw
    0.16
    gulp
    0.16
     down
    0.16
     swal
    0.16
     es
    0.15
    Activations Density 0.033%

    No Known Activations