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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 1
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and their derivatives

    oai_token-act-pair · gpt-4o-mini

    mathematical equations and complex mathematical notation involving trigonometric functions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @felix-tudose
    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
    523
    -0.07
    èŀº
    -0.06
    Prefs
    -0.06
    ÙĪØ¨ÛĮ
    -0.06
    compatible
    -0.06
    ео
    -0.06
    REFIX
    -0.06
    ıng
    -0.06
    _preferences
    -0.06
    PREFIX
    -0.06
    POSITIVE LOGITS
    akis
    0.08
    mür
    0.07
    ym
    0.07
     Exercises
    0.06
    icos
    0.06
    ÙħÙĪÙĦ
    0.06
    ook
    0.06
    ado
    0.06
    rid
    0.06
    aph
    0.06
    Activations Density 0.137%

    No Known Activations