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. 4480
    Prev
    Next
    INDEX
    Explanations

    concepts related to quality and value in services and experiences

    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
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.16
     Berm
    -0.15
    abb
    -0.14
    inue
    -0.14
     же
    -0.13
    AndView
    -0.13
    /cache
    -0.13
    amer
    -0.13
     principle
    -0.13
    /as
    -0.13
    POSITIVE LOGITS
     alike
    0.29
    $MESS
    0.14
     pans
    0.13
    ãĥ©ãĤ¤ãĥ³
    0.13
    .forRoot
    0.13
    arrant
    0.13
    ubi
    0.13
    ysi
    0.13
    .cert
    0.12
    $LANG
    0.12
    Activations Density 0.299%

    No Known Activations