© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 28659
    Prev
    Next
    INDEX
    Explanations

    words beginning with 'sc' where the letters 'c' and 's' are closely associated, even if not a perfect match

    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
    ãģĦãĤĭ
    -0.07
    zers
    -0.07
     sao
    -0.06
     Haut
    -0.06
    hit
    -0.06
    uner
    -0.06
    estroy
    -0.06
    acomment
    -0.06
    onde
    -0.06
    lijke
    -0.06
    POSITIVE LOGITS
    sdale
    0.10
    warz
    0.09
    =sc
    0.09
     hã
    0.09
    ared
    0.08
    atology
    0.08
    chwitz
    0.08
    crow
    0.07
    (SC
    0.07
    /sc
    0.07
    Activations Density 0.034%

    No Known Activations