© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 3207
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or corrections in reasoning

    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
    Negative Logits
     option
    -0.07
     if
    -0.07
    amos
    -0.07
    otland
    -0.06
    ĥ½
    -0.06
     å¦Ĥæŀľ
    -0.06
     options
    -0.06
     perfectly
    -0.06
     Rare
    -0.06
    if
    -0.06
    POSITIVE LOGITS
    ázev
    0.06
    rame
    0.06
     indirectly
    0.06
     navig
    0.06
    uffs
    0.06
    ån
    0.06
    istro
    0.06
    imary
    0.06
    uels
    0.06
    iap
    0.06
    Activations Density 0.063%

    No Known Activations