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-SLIMPJ-OPENR1-RES-32K
    4. 750
    Prev
    Next
    INDEX
    Explanations

    question marks and responses indicating interviews or discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L15R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and 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
    vig
    -0.07
    loor
    -0.06
    ultureInfo
    -0.06
    lyph
    -0.06
     Latina
    -0.06
    leta
    -0.06
    UnityEngine
    -0.06
    zos
    -0.06
    opak
    -0.06
    _Osc
    -0.06
    POSITIVE LOGITS
    âĢĮâĢĮ
    0.07
    agara
    0.06
    Zip
    0.06
    _VARS
    0.06
    swer
    0.06
    uner
    0.06
     grav
    0.06
     speaking
    0.06
    zip
    0.06
    ACLE
    0.06
    Activations Density 0.012%

    No Known Activations