© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their simplifications

    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
    ince
    -0.07
    ãĥ¼ãĥĹ
    -0.07
    imits
    -0.06
    ÑĦек
    -0.06
    elon
    -0.06
     sockfd
    -0.06
    iaux
    -0.06
    gens
    -0.06
    ÑĥÑĢн
    -0.06
    itionally
    -0.06
    POSITIVE LOGITS
    aired
    0.06
     Agr
    0.06
    δÏĮ
    0.06
     Claus
    0.06
    GLOBALS
    0.06
    omers
    0.06
    ark
    0.06
    und
    0.06
    annes
    0.06
    omer
    0.06
    Activations Density 0.113%

    No Known Activations