Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 765
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations involving variables

    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
    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
    itel
    -0.06
    úsqueda
    -0.06
     Jeho
    -0.06
     MetroFramework
    -0.06
    emple
    -0.06
    umd
    -0.06
    REDENTIAL
    -0.06
    że
    -0.06
    ulet
    -0.06
     itself
    -0.06
    POSITIVE LOGITS
    uis
    0.06
    akedirs
    0.06
     pits
    0.06
    oner
    0.06
    vik
    0.06
    rouch
    0.06
    ono
    0.06
    oler
    0.06
    si
    0.06
    orp
    0.06
    Activations Density 0.045%

    No Known Activations