© 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. 288
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas involving sine and cosine functions

    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
    ocr
    -0.07
    obo
    -0.07
    processable
    -0.06
    ibi
    -0.06
     hypert
    -0.06
    asn
    -0.06
    echa
    -0.06
    rocessing
    -0.06
    amel
    -0.06
    odyn
    -0.06
    POSITIVE LOGITS
    ãĥīãĥ«
    0.07
    efa
    0.06
     Sez
    0.06
    ÑĤаж
    0.06
    ož
    0.06
     dny
    0.06
    enstein
    0.06
    PRESSION
    0.06
    etr
    0.06
    ertest
    0.06
    Activations Density 0.046%

    No Known Activations