© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    mathematical properties related to functions and their solutions

    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
    arend
    -0.07
    ÏģÏį
    -0.07
    azzi
    -0.07
    rone
    -0.07
    ÏģÎŃ
    -0.06
    /***/
    -0.06
    ankan
    -0.06
    Ø·Ùĩ
    -0.06
    oleans
    -0.06
    tement
    -0.06
    POSITIVE LOGITS
    oria
    0.07
     Pra
    0.07
     naturally
    0.07
     ya
    0.06
     certainly
    0.06
    olin
    0.06
     ape
    0.06
    ona
    0.06
    ãģªãģĹ
    0.06
    çīĮ
    0.06
    Activations Density 0.072%

    No Known Activations