© 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. 8140
    Prev
    Next
    INDEX
    Explanations

    role and related concepts

    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
    AGMA
    -0.09
    267
    -0.08
    laus
    -0.08
    ajar
    -0.08
     rowNum
    -0.08
    ãĢĢï¾ŀ
    -0.08
     wen
    -0.08
    uggy
    -0.08
    lus
    -0.08
     Rica
    -0.08
    POSITIVE LOGITS
     role
    0.96
     Role
    0.76
    role
    0.74
    Role
    0.66
     roles
    0.63
     ROLE
    0.61
    -role
    0.58
     ÑĢолÑĮ
    0.57
    .role
    0.53
    _role
    0.53
    Activations Density 0.156%

    No Known Activations