© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29801
    Prev
    Next
    INDEX
    Explanations

    segments or breaks in math problems or logic, specifically looking for opening parentheses and the word "darkest" or "is"

    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
     â
    -0.11
     Ãİ
    -0.09
    ÃĤ
    -0.08
     ÃĤ
    -0.07
    Ãİ
    -0.07
    ,
    -0.07
    ât
    -0.07
     Ãĥ
    -0.06
    rement
    -0.06
    â
    -0.06
    POSITIVE LOGITS
    ếp
    0.06
    "urls
    0.06
    âĢ²
    0.06
     luder
    0.06
    Ê
    0.06
    ĻĤ
    0.06
    "indices
    0.06
     âĢº
    0.06
    SenderId
    0.06
    Mocks
    0.06
    Activations Density 0.000%

    No Known Activations