© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 2397
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
    log
    -0.06
     nominal
    -0.06
     deck
    -0.06
    ossal
    -0.06
    roller
    -0.06
     trous
    -0.05
    _traits
    -0.05
     Deck
    -0.05
    nom
    -0.05
     so
    -0.05
    POSITIVE LOGITS
    inea
    0.07
    otts
    0.07
    iyon
    0.06
    irket
    0.06
    enger
    0.06
    annon
    0.06
    á»ģn
    0.06
     voksne
    0.06
    ctions
    0.06
     jedem
    0.06
    Activations Density 0.362%

    No Known Activations