© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27534
    Prev
    Next
    INDEX
    Explanations

    text discussing whether things are distinct or unique, often in the context of math 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
    uv
    -0.06
    hower
    -0.06
    553
    -0.06
    thin
    -0.06
    ucker
    -0.06
    offee
    -0.06
    .echo
    -0.06
    jours
    -0.06
     joint
    -0.06
    -dot
    -0.06
    POSITIVE LOGITS
     uniqueness
    0.16
     unique
    0.15
    unique
    0.13
    Unique
    0.13
     Unique
    0.12
    _unique
    0.12
    (unique
    0.11
    uniq
    0.11
     each
    0.10
     different
    0.10
    Activations Density 0.146%

    No Known Activations