© 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. 402
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation marks in mathematical contexts

    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
    roupon
    -0.07
    onnement
    -0.07
    iscard
    -0.06
     nonatomic
    -0.06
    au
    -0.06
    YLES
    -0.06
     onViewCreated
    -0.06
     uncomment
    -0.06
    gorithm
    -0.06
    andon
    -0.06
    POSITIVE LOGITS
    ebek
    0.07
    .)↵↵↵↵
    0.07
    inki
    0.06
    ESA
    0.06
     dziew
    0.06
    â̦.↵↵
    0.06
    _Params
    0.06
    ÑĥÑĤи
    0.06
    #__
    0.06
    .dm
    0.06
    Activations Density 0.381%

    No Known Activations