© 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. 2049
    Prev
    Next
    INDEX
    Explanations

    expressions related to the discriminant in quadratic equations

    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
    ano
    -0.07
    eno
    -0.07
    วà¸ģ
    -0.07
    amo
    -0.06
    otty
    -0.06
    ago
    -0.06
    hopefully
    -0.06
    ostel
    -0.06
    stri
    -0.06
    esc
    -0.06
    POSITIVE LOGITS
     totiž
    0.07
     ún
    0.07
    czy
    0.07
    inand
    0.06
    LOC
    0.06
     LOC
    0.06
    OutOfBoundsException
    0.06
    ë¡ľëĵľ
    0.06
    رÙĬÙħ
    0.06
     DeÄŁ
    0.06
    Activations Density 0.074%

    No Known Activations