© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 46213
    Prev
    Next
    INDEX
    Explanations

    actions following 'and' or pronouns

    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
    Negative Logits
    å±Ĩ
    -0.09
    Ľå»º
    -0.08
    ê¸Ģ
    -0.08
    ĵ¨
    -0.08
     sweeps
    -0.08
    å±Ĭ
    -0.08
    irim
    -0.08
    ARGIN
    -0.08
    ãģķãĤī
    -0.08
    ÑĢÑıд
    -0.08
    POSITIVE LOGITS
     looks
    0.17
     walk
    0.17
     look
    0.17
     looked
    0.16
     Smile
    0.15
     smile
    0.14
     Look
    0.14
     smiled
    0.14
     Walk
    0.14
    look
    0.13
    Activations Density 0.130%

    No Known Activations