© 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. 19179
    Prev
    Next
    INDEX
    Explanations

    document content and details

    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
     Glover
    -0.09
    onz
    -0.09
    cpt
    -0.09
     Gle
    -0.09
     hereby
    -0.08
     marking
    -0.08
    urg
    -0.08
     producing
    -0.08
    edd
    -0.08
     obey
    -0.08
    POSITIVE LOGITS
     contain
    0.27
     contains
    0.26
     containing
    0.24
    contains
    0.22
     chứa
    0.22
    contain
    0.20
     ÑģодеÑĢж
    0.20
     contiene
    0.20
     Contains
    0.19
     obsah
    0.18
    Activations Density 0.188%

    No Known Activations