© 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. 64738
    Prev
    Next
    INDEX
    Explanations

    we know or see

    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
    ucc
    -0.09
     Kür
    -0.09
    otta
    -0.09
    okie
    -0.09
    attery
    -0.08
    anno
    -0.08
    uib
    -0.08
    ëŀĢ
    -0.08
    578
    -0.08
    oute
    -0.08
    POSITIVE LOGITS
     familiar
    0.20
     пÑĢивÑĭ
    0.20
     norm
    0.15
     usual
    0.14
     accustomed
    0.14
    çĨŁ
    0.14
     normally
    0.14
     experience
    0.13
     familiarity
    0.13
    amiliar
    0.13
    Activations Density 0.074%

    No Known Activations