© 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. 3217
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols used in formulas or equations

    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
    iesel
    -0.06
    uvo
    -0.06
    vo
    -0.06
    rosso
    -0.06
    lice
    -0.06
    erton
    -0.06
     Hop
    -0.06
    ehr
    -0.06
    rv
    -0.05
     AutoMapper
    -0.05
    POSITIVE LOGITS
    åѤ
    0.06
     ëĦ¤ìĿ´íĬ¸
    0.06
    ipse
    0.06
     ìĥĪê¸Ģ
    0.06
    valuate
    0.06
    ãĢĤãĢĤ↵↵
    0.06
    .ToShort
    0.06
    owe
    0.06
    úi
    0.06
    /sources
    0.06
    Activations Density 1.553%

    No Known Activations