© 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. 628
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and expressions involving sums and coefficients

    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
    ãĥ¼ãĥª
    -0.07
     pulse
    -0.06
    Manifest
    -0.06
    urn
    -0.06
     Kaplan
    -0.06
    avenport
    -0.06
    .des
    -0.05
    енÑĤи
    -0.05
    _shell
    -0.05
    utex
    -0.05
    POSITIVE LOGITS
    .LookAndFeel
    0.07
    argout
    0.07
    IDGET
    0.07
    Ðĭ
    0.06
     Crescent
    0.06
    lacak
    0.06
    enor
    0.06
    .joda
    0.06
    ponent
    0.06
    ONUS
    0.06
    Activations Density 0.155%

    No Known Activations