© 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. 313
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and modifications in mathematical functions or concepts

    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
    /ay
    -0.07
    udge
    -0.07
    imiz
    -0.06
    dez
    -0.06
    ajan
    -0.06
    mand
    -0.06
    enne
    -0.06
    ka
    -0.06
     chimney
    -0.06
    rema
    -0.06
    POSITIVE LOGITS
    over
    0.08
    loquent
    0.08
    ¾
    0.07
     venue
    0.07
    /add
    0.07
    overs
    0.07
    ownership
    0.07
    ahoo
    0.07
     tack
    0.07
    /reset
    0.07
    Activations Density 0.035%

    No Known Activations