© 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. 3377
    Prev
    Next
    INDEX
    Explanations

    structural elements of mathematical equations and expressions

    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
    ady
    -0.07
    inka
    -0.06
     Scale
    -0.06
    alice
    -0.06
    ore
    -0.06
     Shore
    -0.06
    nad
    -0.06
     conducting
    -0.06
     exc
    -0.06
    soc
    -0.06
    POSITIVE LOGITS
    ê
    0.07
    важ
    0.07
    redo
    0.07
    олÑİ
    0.07
    /feed
    0.07
     Leban
    0.06
    .tap
    0.06
     Stout
    0.06
    [".
    0.06
    ORMAT
    0.06
    Activations Density 0.142%

    No Known Activations