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. 11-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 8300
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "need to find" in the context of mathematical problem-solving.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L11R
    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.11.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ays
    -0.07
    itten
    -0.06
    quence
    -0.06
    poke
    -0.06
    icky
    -0.06
    omb
    -0.06
    	fflush
    -0.06
    IMA
    -0.06
    bor
    -0.06
    endors
    -0.06
    POSITIVE LOGITS
    Ģ
    0.07
    zim
    0.07
    inalg
    0.07
    :numel
    0.07
     @$_
    0.06
     IDb
    0.06
    iline
    0.06
     hrom
    0.06
    blr
    0.06
    ether
    0.06
    Activations Density 0.164%

    No Known Activations