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. 52
    Prev
    Next
    INDEX
    Explanations

    terms related to intersections in geometry

    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
    oor
    -0.07
    برÛĮ
    -0.07
    uum
    -0.07
    ابر
    -0.06
    licos
    -0.06
    uly
    -0.06
    PLICATE
    -0.06
    aber
    -0.06
    лини
    -0.06
    ogl
    -0.06
    POSITIVE LOGITS
    ing
    0.26
    ed
    0.22
    edBy
    0.13
    ÛĮ
    0.11
    ING
    0.11
    ers
    0.10
    i
    0.09
    ingt
    0.09
    er
    0.09
    edx
    0.09
    Activations Density 0.076%

    No Known Activations