© 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. 17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 23688
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning and geometry terms

    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
     only
    -0.08
    alu
    -0.07
    only
    -0.07
    oyo
    -0.07
    _only
    -0.06
     Only
    -0.06
     never
    -0.06
     ever
    -0.06
     Routes
    -0.06
     merely
    -0.06
    POSITIVE LOGITS
     probably
    0.26
     likely
    0.22
    probably
    0.21
     perhaps
    0.21
     maybe
    0.21
     Probably
    0.20
    Probably
    0.20
     possibly
    0.18
    maybe
    0.17
    perhaps
    0.17
    Activations Density 0.224%

    No Known Activations