© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    The neuron activates for equation or mathematical notation contexts where variables like "l" or "L" are being assigned values.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @trainjumperx

    mathematical symbols and operations

    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
    tright
    -0.08
    Argb
    -0.07
    chio
    -0.06
    à¥ģà¤Ĺत
    -0.06
    timeofday
    -0.06
    RuleContext
    -0.06
    strup
    -0.06
    .pp
    -0.06
    elage
    -0.06
    cak
    -0.06
    POSITIVE LOGITS
    inton
    0.08
    est
    0.07
    640
    0.06
    oui
    0.06
    ams
    0.06
    097
    0.06
     Burl
    0.06
     vern
    0.06
     Marin
    0.06
     av
    0.06
    Activations Density 0.542%

    No Known Activations