Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 71
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and probability 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
    Not in Any Lists

    No Comments

    Negative Logits
    fono
    -0.07
    uler
    -0.07
     Lew
    -0.07
    imary
    -0.06
    ueba
    -0.06
    aben
    -0.06
    aldo
    -0.06
    awai
    -0.06
     Prel
    -0.06
    afen
    -0.06
    POSITIVE LOGITS
     Rarity
    0.08
     Malcolm
    0.07
    ednou
    0.06
    íļį
    0.06
    sville
    0.06
     cavern
    0.06
    kla
    0.06
    elsen
    0.06
    FML
    0.06
    MAND
    0.06
    Activations Density 0.035%

    No Known Activations