© 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. 19256
    Prev
    Next
    INDEX
    Explanations

    even

    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
    GLOSS
    -0.09
    λον
    -0.09
    ENTA
    -0.08
    <|begin_of_text|>
    -0.08
     Evening
    -0.08
    ieval
    -0.08
    eko
    -0.08
     trotz
    -0.08
    egin
    -0.08
    emsp
    -0.08
    POSITIVE LOGITS
     even
    0.92
    çĶļèĩ³
    0.74
     sogar
    0.73
    even
    0.72
     даже
    0.69
     tháºŃm
    0.62
     dokonce
    0.60
     EVEN
    0.58
     Even
    0.57
    Even
    0.54
    Activations Density 0.253%

    No Known Activations