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. 4436
    Prev
    Next
    INDEX
    Explanations

    instances of the term "further," indicating a search for continuative or additional information

    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
    sel
    -0.20
    sell
    -0.17
    ernen
    -0.16
    rum
    -0.14
    anan
    -0.14
    omer
    -0.14
    ses
    -0.14
    SELL
    -0.14
    ngr
    -0.14
    olie
    -0.14
    POSITIVE LOGITS
     than
    0.21
    most
    0.20
    -than
    0.20
    thest
    0.19
    hin
    0.18
    ance
    0.16
     ado
    0.16
     niż
    0.16
    _than
    0.16
    ing
    0.16
    Activations Density 0.044%

    No Known Activations