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. 1533
    Prev
    Next
    INDEX
    Explanations

    references to financial statements or monetary terms

    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
    asser
    -0.20
    alking
    -0.17
    ients
    -0.16
    ass
    -0.15
    ed
    -0.15
    esser
    -0.15
    exe
    -0.14
    àµįà´
    -0.14
    ially
    -0.14
    ess
    -0.14
    POSITIVE LOGITS
    iard
    0.27
    boards
    0.21
    iards
    0.21
    ings
    0.20
    owy
    0.19
    ungs
    0.18
    iams
    0.18
    ows
    0.17
    iterate
    0.17
    patrick
    0.17
    Activations Density 0.080%

    No Known Activations