© 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. 261
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" indicating reasoning or conclusion statements

    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
    üre
    -0.07
    itud
    -0.07
    clar
    -0.07
    hell
    -0.06
    ohn
    -0.06
    usting
    -0.06
    eldon
    -0.06
    ırı
    -0.06
    .functional
    -0.06
    _PROXY
    -0.06
    POSITIVE LOGITS
    abeth
    0.07
    HeaderCode
    0.07
     Rope
    0.06
    PIO
    0.06
    ìĨ
    0.06
    utton
    0.06
    ivet
    0.06
     commission
    0.06
    ajo
    0.06
    ijo
    0.06
    Activations Density 0.036%

    No Known Activations