© 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. 53470
    Prev
    Next
    INDEX
    Explanations

    articles before AI model

    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
     damp
    -0.09
     realpath
    -0.09
     uninsured
    -0.09
     comp
    -0.09
     Warm
    -0.08
     unsur
    -0.08
    odal
    -0.08
     Ebola
    -0.08
    åĪĬ
    -0.08
    ãģĻãģIJ
    -0.08
    POSITIVE LOGITS
     cloud
    0.12
     chat
    0.11
     gener
    0.10
    chat
    0.10
     convers
    0.10
     Readonly
    0.10
     cripp
    0.09
    Chat
    0.09
    Gener
    0.09
     online
    0.09
    Activations Density 0.115%

    No Known Activations