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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 38
    Prev
    Next
    INDEX
    Explanations

    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
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chio
    -0.07
    ĨĴ
    -0.06
     containing
    -0.06
    ext
    -0.06
    ingers
    -0.06
     Mim
    -0.06
    еÑĢед
    -0.06
     swe
    -0.06
    :animated
    -0.06
     ext
    -0.05
    POSITIVE LOGITS
    uju
    0.07
    isas
    0.06
     candid
    0.06
    AREST
    0.06
    iglia
    0.06
    serter
    0.06
    Silver
    0.06
     плеÑĩ
    0.06
     Controls
    0.06
    ìķ½
    0.06
    Activations Density 0.072%

    No Known Activations