© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 26561
    Prev
    Next
    INDEX
    Explanations

    words ending in "ic", "ron", "ence", "ment", "za", "ode", "ious", or "ate" that might relate to mathematical or logical reasoning

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢħ
    -0.09
    gili
    -0.08
     latter
    -0.08
    liest
    -0.08
    alet
    -0.07
    bies
    -0.07
    liness
    -0.07
    ebe
    -0.07
    ening
    -0.07
    allet
    -0.07
    POSITIVE LOGITS
    (sp
    0.10
    ãģĬãĤĬ
    0.08
    /tos
    0.08
    SHIP
    0.07
    hire
    0.07
    .constructor
    0.07
    OUS
    0.07
    리ìķĦ
    0.07
    tes
    0.07
    cy
    0.07
    Activations Density 1.023%

    No Known Activations