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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 15-LLAMASCOPE-OPENR1-RES-32K
    4. 0
    Prev
    Next
    INDEX
    Explanations

    variables and their relationships in mathematical or logical contexts

    oai_token-act-pair · gpt-4o-mini

    mathematical notation and technical mathematical terms.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @felix-tudose

    mathematical terms and concepts like "sums," "vectors," "numerator," "Kneser," "corners," and "siblings" in mathematical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @felix-tudose
    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
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oken
    -0.07
    ernetes
    -0.07
     Wenger
    -0.07
    TRIES
    -0.07
    aukee
    -0.07
    urgence
    -0.07
    orent
    -0.06
    aversable
    -0.06
    u
    -0.06
    Ùħ
    -0.06
    POSITIVE LOGITS
    ues
    0.07
    isel
    0.07
    esk
    0.07
     firsthand
    0.07
    HS
    0.07
    -shaped
    0.07
    ture
    0.07
     f
    0.06
    jack
    0.06
    cae
    0.06
    Activations Density 0.338%

    No Known Activations