© 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. 25792
    Prev
    Next
    INDEX
    Explanations

    uses of the letters x, k, m, or n as variables or coefficients in mathematical equations

    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
    Negative Logits
    issors
    -0.07
    ilar
    -0.06
    ouch
    -0.06
    ária
    -0.06
    estroy
    -0.06
    licht
    -0.06
    okit
    -0.06
    gether
    -0.06
    ilet
    -0.06
     jsonResponse
    -0.06
    POSITIVE LOGITS
    =
    0.08
     ranges
    0.08
     values
    0.08
     being
    0.08
    åĢ¼
    0.07
    istrovstvÃŃ
    0.07
     value
    0.07
     ranging
    0.07
    =?
    0.06
    staking
    0.06
    Activations Density 0.653%

    No Known Activations