Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 11-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 8306
    Prev
    Next
    INDEX
    Explanations

    code and mathematical formula characters, and words related to the size and number of sets

    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/L11R
    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.11.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laz
    -0.07
    ÏĦαÏĤ
    -0.06
    .twig
    -0.06
    æĩ
    -0.06
    ÑĤÑı
    -0.06
    .opensource
    -0.06
     dostan
    -0.06
    -tm
    -0.06
    θλη
    -0.06
    sworth
    -0.06
    POSITIVE LOGITS
    еÑĨ
    0.07
    okers
    0.06
    ué
    0.06
    ecies
    0.06
    ertz
    0.06
     dams
    0.06
    Affected
    0.06
    =count
    0.06
    dimension
    0.06
     weekly
    0.06
    Activations Density 0.428%

    No Known Activations