© 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. 1962
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or calculation of average numbers in a list

    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
    ationToken
    -0.07
    _SID
    -0.06
     æ°¸
    -0.06
    ürn
    -0.06
     partition
    -0.06
     sweep
    -0.06
    938
    -0.06
     fa
    -0.06
    855
    -0.06
    .dispose
    -0.06
    POSITIVE LOGITS
     remaining
    0.23
    åī©
    0.20
     Remaining
    0.20
    remaining
    0.18
    Remaining
    0.17
    _remaining
    0.14
     surviving
    0.13
    æ®ĭ
    0.12
    ä½Ļ
    0.11
     residual
    0.11
    Activations Density 0.195%

    No Known Activations