© 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. 47308
    Prev
    Next
    INDEX
    Explanations

    capacity, manager, summary, expense

    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
    _FC
    -0.10
     Harr
    -0.09
    ToMany
    -0.09
    ÑĤеÑĢи
    -0.09
    aub
    -0.09
    eload
    -0.09
    _RB
    -0.09
    istrar
    -0.09
    ãĥ¼ãģ®
    -0.09
    .updateDynamic
    -0.08
    POSITIVE LOGITS
    thing
    0.27
    imum
    0.24
    iculty
    0.23
    entication
    0.23
    itecture
    0.21
    ratulations
    0.20
    ever
    0.20
    ature
    0.20
    siniz
    0.19
    ยà¸Ļà¸ķร
    0.18
    Activations Density 0.295%

    No Known Activations