© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and formulae

    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
    âĢ¦↵
    -0.21
     âĢ¦↵
    -0.16
     [âĢ¦]↵
    -0.15
    ...↵
    -0.12
    âĢ¦↵↵
    -0.12
    âĢ¦
    -0.11
    âĢ¦it
    -0.11
    âĢ¦and
    -0.11
    âĢ¦but
    -0.10
    âĢ¦I
    -0.10
    POSITIVE LOGITS
    'gc
    0.09
    "urls
    0.08
    >manual
    0.08
    >NN
    0.08
    $fdata
    0.08
    $MESS
    0.08
    ¶ģ
    0.08
    .scalablytyped
    0.07
    .MixedReality
    0.07
     norge
    0.07
    Activations Density 15.916%

    No Known Activations