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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29606
    Prev
    Next
    INDEX
    Explanations

    the word "the" when in close proximity to the word "from"

    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
     yanı
    -0.07
    lane
    -0.07
     outnumber
    -0.07
    ziel
    -0.06
    egie
    -0.06
    arest
    -0.06
    UTILITY
    -0.06
    paRepository
    -0.06
    zel
    -0.06
    .Nodes
    -0.06
    POSITIVE LOGITS
     second
    0.25
    第äºĮ
    0.20
    second
    0.20
     第äºĮ
    0.16
    Second
    0.16
     Second
    0.15
    -second
    0.15
    .second
    0.14
    _second
    0.14
    (second
    0.14
    Activations Density 0.053%

    No Known Activations