© 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. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 3144
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical concepts and their properties, particularly focusing on solutions to equations involving properties like "cute" numbers, composite numbers, and leap year calculations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Negative Logits
    ButtonItem
    -0.07
     muse
    -0.06
    akis
    -0.06
    reeze
    -0.06
    fec
    -0.06
    Fixture
    -0.06
    odoxy
    -0.06
    hend
    -0.06
    owell
    -0.06
     Hlav
    -0.06
    POSITIVE LOGITS
     along
    0.07
    ãĥĥãĥĦ
    0.07
    é©
    0.06
     ext
    0.06
    eeee
    0.06
     also
    0.06
     drop
    0.06
     together
    0.06
     extended
    0.06
     Schwar
    0.06
    Activations Density 0.089%

    No Known Activations