© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 338
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to equations or algorithms

    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
    strand
    -0.07
    \admin
    -0.06
     Comb
    -0.06
    è¡¡
    -0.06
     wake
    -0.06
    ypo
    -0.06
    Slash
    -0.06
    mani
    -0.05
    Faces
    -0.05
    enne
    -0.05
    POSITIVE LOGITS
    692
    0.07
    togroup
    0.06
    ieg
    0.06
    .ISupportInitialize
    0.06
    ±Ð¾ÑĤ
    0.06
     transform
    0.06
    opot
    0.06
    utos
    0.06
    NamedQuery
    0.06
    _geom
    0.06
    Activations Density 0.008%

    No Known Activations