© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29447
    Prev
    Next
    INDEX
    Explanations

    sentences promoting self-improvement, setting a good example to children, or something significant occurring using the words "be" and "example."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĨаÑĢ
    -0.06
     sinc
    -0.06
    511
    -0.06
    /cpu
    -0.06
    _mex
    -0.06
    kaar
    -0.06
    loy
    -0.06
    .enumer
    -0.06
    .cod
    -0.06
    Boom
    -0.05
    POSITIVE LOGITS
     example
    0.25
    example
    0.20
     examples
    0.20
     Example
    0.19
    Example
    0.18
     model
    0.18
     exemple
    0.18
    -example
    0.18
     пÑĢимеÑĢ
    0.17
    ä¾ĭ
    0.17
    Activations Density 0.023%

    No Known Activations