© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1036
    Prev
    Next
    INDEX
    Explanations

    instances of the word "simplify."

    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
    ifice
    -0.06
    aviest
    -0.06
    il
    -0.06
    /member
    -0.06
    anth
    -0.06
    uses
    -0.06
    aeda
    -0.06
    yt
    -0.06
    elsea
    -0.06
    unt
    -0.06
    POSITIVE LOGITS
    oret
    0.08
    etheless
    0.08
    .ibatis
    0.07
    olvers
    0.07
    semblies
    0.06
    è¿Ļ个
    0.06
    uder
    0.06
    ä¸Ģä¸ĭ
    0.06
    VarChar
    0.06
    uition
    0.06
    Activations Density 0.076%

    No Known Activations