© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 2616
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate relationships or shifts in reasoning

    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
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \↵
    -0.07
    ses
    -0.07
     Stub
    -0.07
     fresh
    -0.07
    ested
    -0.07
    ples
    -0.07
    uffix
    -0.06
    ÑĽ
    -0.06
    azing
    -0.06
    ueblo
    -0.06
    POSITIVE LOGITS
    odore
    0.15
    adays
    0.14
    etheless
    0.13
    bsites
    0.11
    atre
    0.10
    alyze
    0.10
    xiety
    0.09
    tlement
    0.09
    atomy
    0.09
    wards
    0.09
    Activations Density 0.588%

    No Known Activations