© 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. 28353
    Prev
    Next
    INDEX
    Explanations

    text that is part of a mathematical proof regarding numbers and/or equations, in particular sections with labels like "For", "Case", or with certain characters such as parentheses

    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
    .dsl
    -0.08
    ijd
    -0.06
    ãĤ¿ãĥ«
    -0.06
     GRE
    -0.06
    burgh
    -0.06
    ÃŃrk
    -0.06
    xca
    -0.06
    اÛĮاÙĨ
    -0.06
    #:
    -0.06
    	strcat
    -0.06
    POSITIVE LOGITS
    dit
    0.08
    ungan
    0.07
    ons
    0.07
    онÑĮ
    0.07
    axon
    0.06
    enn
    0.06
    ant
    0.06
    abin
    0.06
    enzyme
    0.06
    iles
    0.06
    Activations Density 0.106%

    No Known Activations