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. 51
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their relationships, particularly involving variables 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
     latter
    -0.10
    onda
    -0.07
    ifice
    -0.07
    mada
    -0.07
    ìļ´ëį°
    -0.07
    пон
    -0.06
     Incontri
    -0.06
    ©©
    -0.06
    ulet
    -0.06
    uzzi
    -0.06
    POSITIVE LOGITS
    /-
    0.10
    /+
    0.09
    adays
    0.07
    greSQL
    0.06
    bsites
    0.06
    etheless
    0.06
    TOTYPE
    0.06
    atre
    0.06
    odore
    0.06
    ak
    0.06
    Activations Density 0.520%

    No Known Activations