© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 756
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols commonly used in mathematical expressions and 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
    Not in Any Lists

    No Comments

    Negative Logits
    aab
    -0.06
    ignKey
    -0.06
    aises
    -0.06
    isha
    -0.06
    squ
    -0.06
    дн
    -0.06
    aida
    -0.06
     اÙĦرÙħزÙĬØ©
    -0.06
    룴
    -0.06
    íİ
    -0.05
    POSITIVE LOGITS
    aison
    0.07
    ughter
    0.06
     mat
    0.06
    ugi
    0.06
    ì²Ń
    0.06
     lying
    0.06
     polar
    0.06
    igkeit
    0.06
    chap
    0.06
    pha
    0.05
    Activations Density 0.030%

    No Known Activations