© 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. 57382
    Prev
    Next
    INDEX
    Explanations

    blushing embarrassed hesitant

    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
     wink
    -0.10
     herself
    -0.10
     weary
    -0.10
    ughter
    -0.10
    ayah
    -0.10
     impatient
    -0.09
     Mild
    -0.09
     çī©
    -0.09
    agnar
    -0.09
    itel
    -0.09
    POSITIVE LOGITS
     nervous
    0.21
     nerv
    0.20
    idget
    0.17
     неÑĢв
    0.17
     looks
    0.16
     sheep
    0.16
     aver
    0.15
     uncomfortable
    0.15
    hes
    0.15
     blush
    0.15
    Activations Density 0.029%

    No Known Activations