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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 323
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships involving prime and composite numbers

    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
    |
    -0.07
    bes
    -0.07
    engu
    -0.07
    cretion
    -0.06
    οκ
    -0.06
    ano
    -0.06
    кол
    -0.06
    åĽº
    -0.06
     Gale
    -0.06
    lect
    -0.06
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.07
    edia
    0.07
    ,eg
    0.07
    EEDED
    0.06
    Ư
    0.06
    $core
    0.06
     eg
    0.06
    ноÑĩ
    0.06
    mts
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.06
    Activations Density 0.146%

    No Known Activations