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

    Neuronpedia

    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. 453
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to geometric and algebraic concepts

    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
     Spinner
    -0.06
    ore
    -0.06
    uds
    -0.06
     Vance
    -0.06
    916
    -0.06
     Westbrook
    -0.06
    am
    -0.06
    agen
    -0.06
     Rory
    -0.05
     lev
    -0.05
    POSITIVE LOGITS
    ensi
    0.07
    à¸Ļà¸Ń
    0.07
    uter
    0.07
    @js
    0.07
    razione
    0.07
    овÑĸд
    0.06
    berapa
    0.06
    .MixedReality
    0.06
    agini
    0.06
    anner
    0.06
    Activations Density 0.079%

    No Known Activations