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. 29545
    Prev
    Next
    INDEX
    Explanations

    text inside of "[boxed ]" blocks, most likely representing solutions to mathematical problems

    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
    oS
    -0.07
    airo
    -0.06
    xDA
    -0.06
    uria
    -0.06
    isex
    -0.06
    ÄįÃŃ
    -0.06
     à¸Ħาส
    -0.06
    $MESS
    -0.06
     Pert
    -0.06
     ÑĤва
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.08
    tuk
    0.06
    çĦ¶
    0.06
    ds
    0.06
     staying
    0.06
    allery
    0.06
     nowhere
    0.06
    ÑĥÑĢе
    0.06
    ÑĤал
    0.06
    s
    0.06
    Activations Density 0.035%

    No Known Activations