© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28683
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss finding or suggesting a solution

    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
    avan
    -0.07
     equally
    -0.07
     Plain
    -0.06
    zd
    -0.06
     Prest
    -0.06
     also
    -0.06
    许å¤ļ
    -0.06
     gib
    -0.06
    Ń
    -0.06
     similarly
    -0.06
    POSITIVE LOGITS
     those
    0.13
    éĤ£äºĽ
    0.12
    those
    0.12
    Those
    0.11
    éĤ£ä¸ª
    0.10
     Those
    0.10
    éĤ£ç§į
    0.09
     aforementioned
    0.09
    åĪļæīį
    0.08
     tÄĽch
    0.08
    Activations Density 0.020%

    No Known Activations