© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23700
    Prev
    Next
    INDEX
    Explanations

    CamelCase words followed by numbers and special characters, and capitalized words with underscores delineating them.

    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/L17R
    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.17.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±±å¸Ĥ
    -0.08
    å·ŀå¸Ĥ
    -0.08
    ÙģÙĩÙĪÙħ
    -0.07
    obre
    -0.07
    .gb
    -0.06
    _UTF
    -0.06
    .setWindowTitle
    -0.06
    YPD
    -0.06
    :invoke
    -0.06
    à¸ļาà¸Ĺ
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.07
    ](
    0.07
    aran
    0.07
    @nate
    0.07
    _DEPRECATED
    0.07
    @gmail
    0.06
    alloca
    0.06
     Cardinal
    0.06
    olson
    0.06
    odon
    0.06
    Activations Density 0.486%

    No Known Activations