© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 15-LLAMASCOPE-OPENR1-RES-32K
    7. 2261
    Prev
    Next
    INDEX
    Explanations

    instances of weight and mass measurements described in various contexts

    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
    DITION
    -0.06
     wid
    -0.06
    onian
    -0.06
    inar
    -0.06
    kelig
    -0.06
    tae
    -0.06
    ξ
    -0.06
    eking
    -0.06
    rze
    -0.06
    pear
    -0.06
    POSITIVE LOGITS
    -weight
    0.11
    weight
    0.10
     weight
    0.10
    weights
    0.10
    lifting
    0.09
    (weight
    0.09
    .weight
    0.09
    Weight
    0.09
     Weight
    0.08
     weights
    0.08
    Activations Density 0.082%

    No Known Activations