© 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. 27191
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning and logical deduction expressed through "if...then..." statements as well as the definite article "the", often in relation to mathematical variables

    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
    lut
    -0.08
    asio
    -0.07
    è®®
    -0.06
    996
    -0.06
     Heller
    -0.06
    uos
    -0.06
    etti
    -0.06
    uco
    -0.06
    wu
    -0.06
    byn
    -0.06
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.19
     opposite
    0.16
    åı¦
    0.15
    ãĤĤãģĨ
    0.13
     other
    0.13
    对æĸ¹
    0.13
     another
    0.13
     otra
    0.11
     autre
    0.11
     otro
    0.11
    Activations Density 0.056%

    No Known Activations