© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 179
    Prev
    Next
    INDEX
    Explanations

    instances of quoted speech or instructions related to problem-solving

    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
     possibly
    -0.07
    až
    -0.06
     from
    -0.06
    yp
    -0.06
    ↵
    -0.06
     lost
    -0.06
     åĸ
    -0.06
     =
    -0.06
     n
    -0.06
     Imperial
    -0.06
    POSITIVE LOGITS
    .Reporting
    0.08
    ãĥªãĥ¼ãĤº
    0.07
    ocal
    0.07
    /gpl
    0.07
     jadx
    0.06
    BaseContext
    0.06
    \Context
    0.06
    deposit
    0.06
     sécur
    0.06
    eldo
    0.06
    Activations Density 0.090%

    No Known Activations