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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 539
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or relationships

    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
     singleton
    -0.06
    878
    -0.06
    à¤Ĥस
    -0.06
    머ëĭĪ
    -0.06
    agne
    -0.06
    abi
    -0.06
    ardo
    -0.06
    "strconv
    -0.06
    ovich
    -0.06
    swire
    -0.06
    POSITIVE LOGITS
    /*č↵
    0.09
    .club
    0.07
     Barrett
    0.06
     fond
    0.06
    ayah
    0.06
    ëł¥ìĿĦ
    0.06
     Melania
    0.06
    .Generated
    0.06
    #ac
    0.06
    ossil
    0.06
    Activations Density 0.142%

    No Known Activations