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

    Neuronpedia

    Jacobian LensNEW
    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. 1192
    Prev
    Next
    INDEX
    Explanations

    connections between numerical data and their interpretations in a mathematical context

    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
    úa
    -0.07
    ular
    -0.06
    ulaire
    -0.06
    ick
    -0.06
    óz
    -0.06
     something
    -0.06
    InlineData
    -0.06
    -prepend
    -0.06
     Sue
    -0.06
     surrender
    -0.06
    POSITIVE LOGITS
    dle
    0.07
    VERAGE
    0.06
     fitte
    0.06
    ساس
    0.06
    _syntax
    0.06
    à¤ķर
    0.06
    VERSE
    0.06
    кÑĢа
    0.06
    soles
    0.06
    toolbox
    0.06
    Activations Density 0.113%

    No Known Activations