© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1634
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and geometric properties in three-dimensional spaces

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    žel
    -0.07
    achten
    -0.07
    bish
    -0.06
    ìļ´ëį°
    -0.06
    _hdl
    -0.06
    UInteger
    -0.06
    .lst
    -0.06
    ONENT
    -0.06
     Zaman
    -0.06
    stal
    -0.06
    POSITIVE LOGITS
     third
    0.10
    third
    0.08
    第ä¸ī
    0.08
    3
    0.08
     further
    0.07
     Third
    0.07
    Third
    0.07
     THIRD
    0.07
     finally
    0.07
    erc
    0.07
    Activations Density 0.134%

    No Known Activations