© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27661
    Prev
    Next
    INDEX
    Explanations

    code snippets in different languages that might possibly be assertions, or at least lines of code, and also XML or HTML closing or opening tags and some enum definitions

    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/L21R
    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.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yst
    -0.07
    iry
    -0.06
    an
    -0.06
    áno
    -0.06
    ibern
    -0.06
     Kund
    -0.06
    ÑĢоз
    -0.06
     stre
    -0.06
     pil
    -0.06
    erton
    -0.06
    POSITIVE LOGITS
    0.09
    áºŃu
    0.07
    ilha
    0.06
    Ñĩим
    0.06
    çĭ¼
    0.06
    apesh
    0.06
    SCRI
    0.06
     åĿ
    0.06
    Ľi
    0.06
    uddy
    0.06
    Activations Density 0.040%

    No Known Activations