© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 28188
    Prev
    Next
    INDEX
    Explanations

    words related to organization(columns and rows), measuring things(sums and signal), and living organisms(lungs and hearts)

    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
    .sul
    -0.07
    çļĦäºĭæĥħ
    -0.07
    ãĤ¹ãĥĨãĤ£
    -0.07
    bidden
    -0.06
    idden
    -0.06
    ysi
    -0.06
    oldt
    -0.06
    _INCLUDED
    -0.06
    ÑĥÑĢн
    -0.06
     onHide
    -0.06
    POSITIVE LOGITS
     syndrome
    0.09
     Syndrome
    0.07
    -wide
    0.07
    esser
    0.07
    elines
    0.06
    ç¬
    0.06
    anvas
    0.06
     compared
    0.06
     posture
    0.06
    emean
    0.06
    Activations Density 0.102%

    No Known Activations