© 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. 53282
    Prev
    Next
    INDEX
    Explanations

    vários sites

    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
    æĮ
    -0.10
    ald
    -0.10
    IOR
    -0.09
    ients
    -0.09
    illa
    -0.09
    aldo
    -0.09
    cheid
    -0.09
    pek
    -0.09
     nuest
    -0.09
    411
    -0.09
    POSITIVE LOGITS
    erry
    0.13
    ass
    0.11
    rapper
    0.11
    enced
    0.10
    ê
    0.10
    adia
    0.10
    iver
    0.10
    omite
    0.09
    urus
    0.09
    angl
    0.09
    Activations Density 0.032%

    No Known Activations