© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    sequences of punctuation marks followed by contextual phrases or clauses

    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
    -0.08
     .
    -0.07
    che
    -0.07
    int
    -0.07
     balance
    -0.07
     balanced
    -0.07
    bal
    -0.07
    Int
    -0.07
    /
    -0.06
    <|end_of_text|>
    -0.06
    POSITIVE LOGITS
    #__
    0.07
     koc
    0.07
    ÑĶм
    0.07
    _Impl
    0.07
    Äįel
    0.06
     kalk
    0.06
     Sür
    0.06
    Ïģκ
    0.06
    .dtd
    0.06
    дина
    0.06
    Activations Density 1.401%

    No Known Activations