© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 210
    Prev
    Next
    INDEX
    Explanations

    relationships between parts and segments 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
    wap
    -0.08
    amin
    -0.06
     Nicholson
    -0.06
    åŁºäºİ
    -0.06
    ¾
    -0.06
    Æ¡
    -0.06
    ÑĦоÑĢ
    -0.06
    rol
    -0.06
    dda
    -0.05
    fore
    -0.05
    POSITIVE LOGITS
     whereas
    0.16
     Whereas
    0.12
     versus
    0.10
     while
    0.10
    ï¼ĮèĢĮ
    0.09
     vs
    0.09
    èĢĮ
    0.09
    while
    0.07
     iar
    0.07
     èĢĮ
    0.07
    Activations Density 0.112%

    No Known Activations