© 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. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 280
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lic
    -0.07
    145
    -0.07
     argument
    -0.07
    231
    -0.06
     gone
    -0.06
    887
    -0.06
    èĻļ
    -0.06
    pu
    -0.06
     num
    -0.06
    sole
    -0.06
    POSITIVE LOGITS
    á»īnh
    0.08
    egov
    0.07
    İT
    0.07
    rawer
    0.07
    Assignable
    0.06
    _KeyDown
    0.06
    =".$_
    0.06
    nech
    0.06
    ognito
    0.06
    /Dk
    0.06
    Activations Density 0.122%

    No Known Activations