© 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. 28472
    Prev
    Next
    INDEX
    Explanations

    words/phrases relating to systems or processes of a business, but also has a focus on "ness"-ending words beyond that context.

    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
     Include
    -0.07
    Was
    -0.07
     includes
    -0.07
     include
    -0.06
     Was
    -0.06
    endon
    -0.06
    include
    -0.06
    was
    -0.06
     consist
    -0.06
    ’m
    -0.06
    POSITIVE LOGITS
     are
    0.21
    éĥ½æĺ¯
    0.16
     were
    0.15
     éĥ½
    0.14
     Äijá»ģu
    0.14
    ï¼Įéĥ½
    0.14
    éĥ½ä¼ļ
    0.14
    _are
    0.14
     são
    0.14
     aren
    0.14
    Activations Density 0.154%

    No Known Activations