© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 28145
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that often occur together such as 'as the', 'of the', 'they contain some'

    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/L21R
    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.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slu
    -0.07
    eler
    -0.07
    efault
    -0.06
    Äįást
    -0.06
    zap
    -0.06
    ávÄĽ
    -0.06
    rome
    -0.06
    809
    -0.06
    lectron
    -0.06
    ube
    -0.06
    POSITIVE LOGITS
     among
    0.30
     amongst
    0.25
    among
    0.24
     Among
    0.24
    Among
    0.22
     one
    0.21
    ä¹ĭä¸Ģ
    0.20
     salah
    0.17
    åħ¶ä¸Ń
    0.16
     ranks
    0.14
    Activations Density 0.045%

    No Known Activations