© 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. 1910
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving variables and equations

    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
     impro
    -0.06
    rier
    -0.06
    (LogLevel
    -0.06
    omu
    -0.06
    äºĮ人
    -0.06
    lah
    -0.06
    nown
    -0.06
     suk
    -0.06
    ogo
    -0.05
    δά
    -0.05
    POSITIVE LOGITS
     either
    0.09
     selected
    0.08
     whichever
    0.08
    either
    0.07
     chosen
    0.07
     chose
    0.07
     Either
    0.07
     EITHER
    0.07
    selected
    0.07
     randomly
    0.07
    Activations Density 0.061%

    No Known Activations