© 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. 29791
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning, especially around proving or checking a solution

    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
    ÅĤem
    -0.06
     elsewhere
    -0.06
    S
    -0.06
    ington
    -0.05
    Neither
    -0.05
    ί
    -0.05
    ount
    -0.05
    asse
    -0.05
     EITHER
    -0.05
    егоÑĢ
    -0.05
    POSITIVE LOGITS
     all
    0.42
    æīĢæľī
    0.37
     semua
    0.28
    åħ¨éĥ¨
    0.27
     wszyst
    0.27
    ãģĻãģ¹ãģ¦
    0.26
     ALL
    0.26
     вÑģеÑħ
    0.25
     everything
    0.25
     모ëĵł
    0.24
    Activations Density 0.635%

    No Known Activations