© 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. 403
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ambiguity or lack of clear specifications

    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
    ica
    -0.07
    HING
    -0.06
     Arthur
    -0.06
     Kad
    -0.06
     karÄ±ÅŁ
    -0.06
     overnight
    -0.06
     Sed
    -0.06
     certain
    -0.06
     v
    -0.06
     refr
    -0.06
    POSITIVE LOGITS
     Explicit
    0.07
    explicit
    0.07
    MemoryWarning
    0.07
     explicit
    0.06
    pite
    0.06
    Explicit
    0.06
     kå
    0.06
     damer
    0.06
    è¿Ļä¸Ģ
    0.06
     explicitly
    0.06
    Activations Density 0.062%

    No Known Activations