© 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. 24017
    Prev
    Next
    INDEX
    Explanations

    mathematical, numeric, and code-related text like section headers, intervals, and primes

    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
    ival
    -0.07
     Mile
    -0.06
    .Unicode
    -0.06
    I
    -0.06
     Tier
    -0.06
    content
    -0.06
     somehow
    -0.06
    u
    -0.06
    t
    -0.06
     solar
    -0.06
    POSITIVE LOGITS
    aç
    0.08
    ï¼ĮåŃĺäºİ
    0.07
    bÃŃr
    0.07
    .decorate
    0.06
    ebek
    0.06
    Vectorizer
    0.06
    NTAX
    0.06
    ζί
    0.06
    496
    0.06
     RouteServiceProvider
    0.06
    Activations Density 0.212%

    No Known Activations