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. 8371
    Prev
    Next
    INDEX
    Explanations

    a variety of different words, possibly with no clear unifying theme.

    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
    idal
    -0.07
    uty
    -0.07
    acht
    -0.07
    nell
    -0.07
    riel
    -0.07
    enal
    -0.06
    IZED
    -0.06
    æ²¢
    -0.06
    üzel
    -0.06
    zahl
    -0.06
    POSITIVE LOGITS
    able
    0.18
    ings
    0.16
    ÂŃing
    0.13
    ers
    0.13
    ing
    0.12
    ability
    0.11
    ables
    0.11
    ABLE
    0.11
    ableObject
    0.10
    ING
    0.10
    Activations Density 0.129%

    No Known Activations