© 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. 312
    Prev
    Next
    INDEX
    Explanations

    numerical values or ratios related to mathematical expressions

    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
     ($)
    -0.06
    dub
    -0.06
    plus
    -0.06
    Plus
    -0.06
    leur
    -0.06
    dera
    -0.06
    omo
    -0.06
    ynam
    -0.06
    esk
    -0.06
    emin
    -0.06
    POSITIVE LOGITS
    گار
    0.06
    jadi
    0.06
    amina
    0.06
     åĮĸ
    0.06
     baiser
    0.06
    _literals
    0.06
    radu
    0.06
     nÄĽkter
    0.06
    hek
    0.06
    /msg
    0.06
    Activations Density 0.099%

    No Known Activations