© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 2197
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
    hattan
    -0.07
    quil
    -0.06
    ova
    -0.06
    arra
    -0.06
    agli
    -0.06
    newline
    -0.06
    **/↵↵
    -0.06
    .RowStyle
    -0.06
    itters
    -0.06
    names
    -0.06
    POSITIVE LOGITS
    ras
    0.07
    ITEM
    0.06
    oman
    0.06
     affair
    0.06
    ashi
    0.06
    ë¬
    0.06
    _________________↵↵
    0.06
    Merchant
    0.06
    CONTEXT
    0.06
    633
    0.06
    Activations Density 0.292%

    No Known Activations