© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 683
    Prev
    Next
    INDEX
    Explanations

    contexts involving mathematical properties and 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
    574
    -0.07
    olet
    -0.07
    855
    -0.06
    roti
    -0.06
    rganization
    -0.06
    gregation
    -0.06
    tern
    -0.06
    318
    -0.06
    958
    -0.06
    497
    -0.06
    POSITIVE LOGITS
    æ²¢
    0.06
    ÙĪÙĦÛĮ
    0.06
     غÙĬر
    0.06
    à¸Ńà¸Ń
    0.06
     غÛĮر
    0.06
    äºľ
    0.06
    PRINTF
    0.06
    combe
    0.06
    non
    0.06
    楽
    0.06
    Activations Density 0.162%

    No Known Activations