© 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
    2. DeepSeek-R1-Dist-Llama-8B
    3. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 23974
    Prev
    Next
    INDEX
    Explanations

    technical discourse concerning combinations and algorithms.

    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
    quota
    -0.06
    Sorting
    -0.06
     sorting
    -0.06
    vester
    -0.06
     pa
    -0.06
    ãĥ¼ãĥł
    -0.06
    ANG
    -0.06
    ãĤ¹ãĤ¿ãĥ¼
    -0.06
     sh
    -0.06
     progress
    -0.06
    POSITIVE LOGITS
     chain
    0.10
    chain
    0.09
     chains
    0.08
    (chain
    0.08
     length
    0.08
     Chain
    0.08
    _chain
    0.07
    éķ¿åº¦
    0.07
     Chains
    0.07
     Length
    0.07
    Activations Density 0.439%

    No Known Activations