© 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
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 348
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their associated patterns in 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
    ADB
    -0.07
    afone
    -0.07
    ัศ
    -0.06
    ãĥ«ãĤ¯
    -0.06
    .Unmarshal
    -0.06
    FML
    -0.06
    Fully
    -0.06
    akra
    -0.06
    rchive
    -0.06
    ĵåIJį
    -0.06
    POSITIVE LOGITS
     indeed
    0.08
     Indeed
    0.08
    Indeed
    0.07
     totiž
    0.07
    218
    0.07
    vel
    0.06
    åİŁæĿ¥
    0.06
     intervention
    0.06
    heid
    0.06
     First
    0.06
    Activations Density 0.189%

    No Known Activations