Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 111
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "after 9" or related constructions

    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
    zelf
    -0.08
    жÑĥ
    -0.07
    swick
    -0.07
    vd
    -0.07
     norge
    -0.06
    nap
    -0.06
    rowse
    -0.06
    unda
    -0.06
    ErrorException
    -0.06
    Violation
    -0.06
    POSITIVE LOGITS
    words
    0.12
    thought
    0.11
    wards
    0.11
    word
    0.10
    ward
    0.09
    /b
    0.09
     initial
    0.08
    effects
    0.08
    no
    0.07
     initially
    0.07
    Activations Density 0.048%

    No Known Activations