© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29141
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs including references to columns and areas

    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
    plx
    -0.07
    yleft
    -0.06
    rych
    -0.06
     buffering
    -0.06
    hq
    -0.06
    orra
    -0.06
    strup
    -0.06
     Exterior
    -0.06
    ovah
    -0.06
    opia
    -0.06
    POSITIVE LOGITS
     space
    0.40
    space
    0.31
    空éĹ´
    0.31
     Space
    0.31
    -space
    0.30
    Space
    0.29
    _space
    0.27
     espacio
    0.25
     SPACE
    0.25
    (space
    0.24
    Activations Density 0.090%

    No Known Activations