© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 2755
    Prev
    Next
    INDEX
    Explanations

    transitions between negative and positive values in mathematical functions

    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
    atte
    -0.07
     porr
    -0.07
    ffects
    -0.06
    illi
    -0.06
    abus
    -0.06
    amide
    -0.06
     proced
    -0.06
    iveau
    -0.06
    zan
    -0.06
    .GetById
    -0.06
    POSITIVE LOGITS
     into
    0.06
    uji
    0.06
    ãģĭãģ«
    0.06
     FileMode
    0.06
    ekyll
    0.06
     зад
    0.06
    olson
    0.06
    ãģĵãģ¨ãģ«
    0.06
     Pip
    0.06
    bst
    0.05
    Activations Density 0.039%

    No Known Activations