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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29072
    Prev
    Next
    INDEX
    Explanations

    passsages where someone is explaining math, often with an emphasis on corrections to previous logic

    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
    oeff
    -0.07
    bero
    -0.07
     undercut
    -0.06
    uspended
    -0.06
    æķı
    -0.06
     unreliable
    -0.06
    AMB
    -0.06
    pto
    -0.06
    AndWait
    -0.06
    MF
    -0.06
    POSITIVE LOGITS
     forget
    0.26
     forgetting
    0.23
     overlook
    0.23
    å¿ĺ
    0.23
     neglect
    0.23
    forget
    0.22
     forgot
    0.22
     ignores
    0.21
    忽
    0.21
     ignore
    0.20
    Activations Density 0.105%

    No Known Activations