© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 23183
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning in the text

    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/L17R
    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.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remainder
    -0.07
    ,'#
    -0.06
    urgeon
    -0.06
     remaining
    -0.06
    713
    -0.06
     оÑģÑĤан
    -0.06
    UMB
    -0.06
    remaining
    -0.06
    unker
    -0.05
    pan
    -0.05
    POSITIVE LOGITS
     smallest
    0.15
     earliest
    0.15
     lowest
    0.12
     first
    0.11
    lowest
    0.11
    Minimum
    0.10
     minimum
    0.10
     minimal
    0.10
     Minimum
    0.10
     shortest
    0.10
    Activations Density 0.159%

    No Known Activations