© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 2205
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically the comma character

    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
    142
    -0.06
     ë³´ë©´
    -0.06
    ãģ»ãģĨ
    -0.06
    reh
    -0.06
    UIS
    -0.06
    >Show
    -0.06
    92
    -0.06
    ui
    -0.06
    -based
    -0.06
    /on
    -0.06
    POSITIVE LOGITS
    onis
    0.06
    ché
    0.06
    OfType
    0.06
    isman
    0.06
    ability
    0.06
    kyt
    0.06
    _firestore
    0.06
     _{}
    0.06
    .zh
    0.06
    ICODE
    0.06
    Activations Density 0.083%

    No Known Activations