Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29467
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is discussing their problem-solving process

    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
    _tol
    -0.07
    ertz
    -0.06
    ema
    -0.06
    otec
    -0.06
     Zust
    -0.06
    .Cursors
    -0.06
     lightly
    -0.05
    çŀ
    -0.05
    سط
    -0.05
     Drawer
    -0.05
    POSITIVE LOGITS
     already
    0.12
    å·²ç»ı
    0.10
     å·²
    0.10
    already
    0.10
     Already
    0.09
     Äijã
    0.08
     did
    0.08
    Already
    0.08
    've
    0.08
    ’ve
    0.07
    Activations Density 0.033%

    No Known Activations