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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 342
    Prev
    Next
    INDEX
    Explanations

    patterns and relationships in numerical data, particularly focusing on factors and sums

    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
    âĢĮâĢĮ
    -0.06
    edException
    -0.06
    ervo
    -0.06
    ivative
    -0.06
    çīĩ
    -0.06
    UCH
    -0.06
    _EP
    -0.06
     Harden
    -0.06
    /Gate
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
    itemap
    0.06
    èħ¹
    0.06
    AIT
    0.06
     pul
    0.06
     {-
    0.06
    ÑĩÑĥ
    0.06
    ebek
    0.06
    ализи
    0.06
    ait
    0.06
     dis
    0.06
    Activations Density 0.379%

    No Known Activations