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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 45
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations involving variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    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
     “
    -0.07
     possibly
    -0.07
     [â̦]
    -0.07
     Sh
    -0.07
     thru
    -0.07
    â̦
    -0.07
     eventual
    -0.07
    ...
    -0.07
    .↵↵
    -0.07
     [â̦]↵
    -0.07
    POSITIVE LOGITS
     dán
    0.07
     dilig
    0.07
     öden
    0.07
     moden
    0.07
    Ñģол
    0.07
     canh
    0.07
    olist
    0.07
     escorte
    0.07
     ür
    0.07
     kabil
    0.07
    Activations Density 0.137%

    No Known Activations