© 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. 27974
    Prev
    Next
    INDEX
    Explanations

    things that are assigned, marked, or laid out in space or time

    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
    ippi
    -0.07
     Dalton
    -0.06
    μÏĢο
    -0.06
    ãģĹãĤĩ
    -0.05
    .respond
    -0.05
    ccione
    -0.05
     pstmt
    -0.05
    urat
    -0.05
     vej
    -0.05
    ÏĪ
    -0.05
    POSITIVE LOGITS
     dedicated
    0.29
     reserved
    0.29
     devoted
    0.26
     reserve
    0.23
    reserved
    0.22
     Dedicated
    0.22
     dedic
    0.22
     dedicate
    0.21
     Reserved
    0.20
    ded
    0.19
    Activations Density 0.051%

    No Known Activations