© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27689
    Prev
    Next
    INDEX
    Explanations

    uses words and phrases that indicate the continuation of mathematical problem solving, like 'so', 'the', 'wait', 'making', 'therefore'

    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
    slaught
    -0.06
    841
    -0.06
    ocks
    -0.06
    ÑĨÑİ
    -0.05
    .parametrize
    -0.05
    upe
    -0.05
    ertino
    -0.05
     smrt
    -0.05
     nackte
    -0.05
     zwarte
    -0.05
    POSITIVE LOGITS
     overall
    0.56
    overall
    0.43
    Overall
    0.42
     Overall
    0.42
     entire
    0.31
     whole
    0.30
    æķ´ä¸ª
    0.30
     altogether
    0.28
     total
    0.27
     ìłĦì²´
    0.25
    Activations Density 0.619%

    No Known Activations