© 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. 38416
    Prev
    Next
    INDEX
    Explanations

    supporting evidence and sources

    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
    ool
    -0.10
    aden
    -0.09
     ASN
    -0.09
     pic
    -0.09
     wis
    -0.08
     ç¿
    -0.08
     rout
    -0.08
    ovich
    -0.08
    :;\n
    -0.08
    /g
    -0.08
    POSITIVE LOGITS
     supporting
    0.33
     support
    0.31
     backing
    0.29
    æĶ¯æĮģ
    0.29
     supports
    0.28
    support
    0.28
    Support
    0.25
     поддеÑĢж
    0.25
     há»Ĺ
    0.24
     Supporting
    0.24
    Activations Density 0.107%

    No Known Activations