© 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. 47501
    Prev
    Next
    INDEX
    Explanations

    agreement shall

    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
    kea
    -0.09
    ê¸Ķ
    -0.09
    amma
    -0.08
    itchens
    -0.08
     Slee
    -0.08
    achuset
    -0.08
     lifes
    -0.08
    perms
    -0.08
    gorm
    -0.08
    llum
    -0.08
    POSITIVE LOGITS
     shall
    0.18
    shall
    0.15
     Shall
    0.13
     SHALL
    0.12
    hall
    0.10
    )("
    0.09
     incident
    0.09
     fur
    0.09
    ita
    0.09
     referred
    0.09
    Activations Density 0.097%

    No Known Activations