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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 587
    Prev
    Next
    INDEX
    Explanations

    repetitive punctuation marks, specifically commas and colons

    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
     Ekon
    -0.06
     Burr
    -0.06
    cope
    -0.06
    unma
    -0.06
    ï¼Ĭ
    -0.06
    ÑģÑĮого
    -0.06
     koc
    -0.06
    ddit
    -0.06
    رÙĬÙħ
    -0.06
     Hlav
    -0.06
    POSITIVE LOGITS
    duct
    0.06
    .h
    0.06
     bored
    0.06
    ductive
    0.06
    -Ñħ
    0.06
    bris
    0.06
    ény
    0.06
    /WebAPI
    0.06
    pheres
    0.06
    adian
    0.05
    Activations Density 0.059%

    No Known Activations