© 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. 26010
    Prev
    Next
    INDEX
    Explanations

    mathematical size descriptions, and geometric concepts such as area and volume

    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
    ataire
    -0.08
    Äįer
    -0.08
    dling
    -0.07
    raud
    -0.07
     Erotik
    -0.07
    vá
    -0.07
    oref
    -0.06
    plier
    -0.06
    atoi
    -0.06
    HTTPHeader
    -0.06
    POSITIVE LOGITS
     given
    0.24
     Given
    0.19
    given
    0.18
    Given
    0.18
     GIVEN
    0.16
    _given
    0.15
     fixed
    0.13
     same
    0.13
    same
    0.12
    缸åIJĮ
    0.12
    Activations Density 0.071%

    No Known Activations