© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27361
    Prev
    Next
    INDEX
    Explanations

    the start of a math problem being solved, and also any talk of numbers or probability

    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
    елик
    -0.08
    åħ¶ä¸Ń
    -0.07
    favorites
    -0.07
    алÑİ
    -0.07
    ipherals
    -0.07
    ëł¹
    -0.06
    hotmail
    -0.06
     zdrav
    -0.06
    obus
    -0.06
    .IContainer
    -0.06
    POSITIVE LOGITS
     airplane
    0.07
     movie
    0.07
    æģ
    0.07
     medical
    0.06
     animal
    0.06
    omp
    0.06
    a
    0.06
    icient
    0.06
    114
    0.06
    movie
    0.06
    Activations Density 0.079%

    No Known Activations