© 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. 26341
    Prev
    Next
    INDEX
    Explanations

    transitions of time, like "before long", "eventually", "until", and "then"

    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
     Twice
    -0.08
    elda
    -0.06
    isko
    -0.06
    enko
    -0.06
     Ahead
    -0.06
     twice
    -0.06
    dzi
    -0.06
    rea
    -0.06
    æ®ĭ
    -0.06
    lop
    -0.05
    POSITIVE LOGITS
     soon
    0.29
     Soon
    0.23
    Soon
    0.22
    soon
    0.21
     eventually
    0.15
     Eventually
    0.14
    Eventually
    0.13
     before
    0.13
     sooner
    0.12
     gradually
    0.12
    Activations Density 0.024%

    No Known Activations