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-RES-32K
    4. 8102
    Prev
    Next
    INDEX
    Explanations

    concepts related to maintenance and sustainability

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B
    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
    arih
    -0.15
    eness
    -0.15
    iaux
    -0.15
    226
    -0.14
    ildo
    -0.14
    enes
    -0.14
    essler
    -0.14
    .Commands
    -0.14
    256
    -0.13
    letion
    -0.13
    POSITIVE LOGITS
    ably
    0.20
    ascus
    0.16
    á»ı
    0.16
    osaur
    0.16
    lander
    0.15
    ance
    0.15
    ment
    0.15
    MSG
    0.15
    prus
    0.15
     momentum
    0.14
    Activations Density 0.041%

    No Known Activations