© 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. 290
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conditional phrases signaling conclusions or steps in reasoning

    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
    oded
    -0.07
    ograd
    -0.07
    angep
    -0.06
    007
    -0.06
    —that
    -0.06
    itou
    -0.06
    opy
    -0.06
    oute
    -0.06
    lector
    -0.06
    093
    -0.06
    POSITIVE LOGITS
    ijd
    0.08
    mast
    0.07
    æĤ
    0.06
    ESCO
    0.06
    âķij
    0.06
    еÑģÑĮ
    0.06
    éĽĦ
    0.06
    ī
    0.06
    à¥ĭà¤ľ
    0.06
     intended
    0.06
    Activations Density 0.130%

    No Known Activations