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. 15-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 781
    Prev
    Next
    INDEX
    Explanations

    key elements and themes related to familial relationships and connections

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L15R
    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.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uddle
    -0.06
    /includes
    -0.06
    é¡ĺ
    -0.06
     said
    -0.06
    ees
    -0.06
    士
    -0.06
     ed
    -0.06
    ève
    -0.06
    æĦ¿
    -0.06
     C
    -0.06
    POSITIVE LOGITS
     kå
    0.08
    /Branch
    0.07
    iosper
    0.07
    632
    0.07
     RedirectTo
    0.06
     *----------------------------------------------------------------
    0.06
    erç
    0.06
    711
    0.06
    âĺĨ
    0.06
    QRST
    0.06
    Activations Density 0.043%

    No Known Activations