© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    providing the reason why

    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
    errick
    -0.09
    aben
    -0.09
     Swan
    -0.08
    gles
    -0.08
     purely
    -0.08
    .toObject
    -0.08
    ocale
    -0.08
     magn
    -0.07
    YPD
    -0.07
    ubs
    -0.07
    POSITIVE LOGITS
     because
    0.64
     Because
    0.54
    because
    0.54
    åĽłä¸º
    0.54
    Because
    0.50
     porque
    0.47
     karena
    0.44
    ecause
    0.42
     поÑĤомÑĥ
    0.42
     vì
    0.41
    Activations Density 0.158%

    No Known Activations