© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 26112
    Prev
    Next
    INDEX
    Explanations

    math or physics related documents, notably where a variable equals some value that can be substituted 'for' some variable, or otherwise involve the word 'for' with math variables

    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
    deaux
    -0.06
    vang
    -0.06
    adders
    -0.06
    posables
    -0.06
    eum
    -0.06
    имв
    -0.06
    onu
    -0.06
    (åľŁ
    -0.06
    еÑĢеж
    -0.06
    leftright
    -0.05
    POSITIVE LOGITS
     some
    0.39
    some
    0.33
     somewhere
    0.32
     Some
    0.32
    Some
    0.30
     SOME
    0.27
    æŁIJ
    0.27
    _some
    0.26
    .some
    0.25
     quelque
    0.25
    Activations Density 0.286%

    No Known Activations