© 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. 329
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas and parentheses

    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
    _BS
    -0.07
    TRS
    -0.06
    ushi
    -0.06
    afx
    -0.06
    (Source
    -0.06
     hybrid
    -0.06
    CRET
    -0.06
    SCRI
    -0.06
    Nib
    -0.06
    ÏĦα
    -0.06
    POSITIVE LOGITS
     only
    0.07
    ison
    0.07
    illions
    0.07
     focus
    0.07
     Only
    0.06
    ONLY
    0.06
     Sul
    0.06
     deal
    0.06
    only
    0.06
    JI
    0.06
    Activations Density 0.059%

    No Known Activations