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

    Neuronpedia

    Jacobian LensNEW
    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. 27880
    Prev
    Next
    INDEX
    Explanations

    breaks in an explanation involving both math and natural language

    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
     therefore
    -0.47
     Therefore
    -0.37
    Therefore
    -0.35
     thus
    -0.34
     hence
    -0.30
     donc
    -0.29
    åĽłæѤ
    -0.29
    thus
    -0.28
    ï¼ĮåĽłæѤ
    -0.28
     daher
    -0.27
    POSITIVE LOGITS
    جا
    0.06
    andal
    0.06
    ayment
    0.06
    (EXPR
    0.06
    اظ
    0.05
    Spacer
    0.05
    calculator
    0.05
    peare
    0.05
    494
    0.05
    _DISABLE
    0.05
    Activations Density 0.058%

    No Known Activations