© 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. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 29276
    Prev
    Next
    INDEX
    Explanations

    references to opinions, problems and concerns

    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
    eltas
    -0.06
    cisi
    -0.06
    ruc
    -0.06
     оÑģновном
    -0.06
    thag
    -0.06
    weetalert
    -0.06
    pytest
    -0.06
    alez
    -0.06
    eç
    -0.06
    mÃ¼ÅŁ
    -0.06
    POSITIVE LOGITS
     these
    0.10
     this
    0.08
    these
    0.08
    è¿ĻäºĽ
    0.08
     those
    0.08
    this
    0.07
     contemporary
    0.07
     most
    0.07
     Mr
    0.07
    éĤ£äºĽ
    0.07
    Activations Density 0.047%

    No Known Activations