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. 140
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical references

    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
     Hats
    -0.06
     Watts
    -0.06
    atts
    -0.06
     happen
    -0.06
     happens
    -0.06
     Wy
    -0.06
    esel
    -0.06
    ween
    -0.06
    Com
    -0.06
     queryParams
    -0.06
    POSITIVE LOGITS
     effects
    0.07
     benefit
    0.07
    kili
    0.07
     effectiveness
    0.07
    Effects
    0.07
    кÑĥÑģ
    0.07
     benefits
    0.06
     Effects
    0.06
     subs
    0.06
     benefited
    0.06
    Activations Density 0.067%

    No Known Activations