© 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. 300
    Prev
    Next
    INDEX
    Explanations

    occurrences of the label "OA" in relation to geometric figures and calculations

    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
    ka
    -0.13
    li
    -0.12
    nya
    -0.10
    ko
    -0.09
    bo
    -0.09
    kl
    -0.09
    so
    -0.09
    che
    -0.09
    ning
    -0.09
    la
    -0.09
    POSITIVE LOGITS
    Ùĭ
    0.11
    ’nın
    0.09
    frica
    0.08
    'nın
    0.08
    ipur
    0.08
    ughter
    0.08
    ught
    0.08
    flow
    0.08
    election
    0.08
    heading
    0.08
    Activations Density 0.151%

    No Known Activations