© 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. 380
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    CTS
    -0.06
    haps
    -0.06
     spons
    -0.06
    à¥Ģण
    -0.06
    ô
    -0.06
    umat
    -0.06
    otel
    -0.06
    olen
    -0.06
     Uhr
    -0.06
    unami
    -0.06
    POSITIVE LOGITS
     imag
    0.07
    еÑĢÑĪ
    0.07
    pedia
    0.07
    PageRoute
    0.07
    htt
    0.06
    aget
    0.06
    bach
    0.06
    ancement
    0.06
    _firestore
    0.06
    baugh
    0.06
    Activations Density 0.106%

    No Known Activations