© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 27069
    Prev
    Next
    INDEX
    Explanations

    discourse markers like "however", "but", "assume", and "say", or items happening simultaneously

    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
    ä¸Ģ个
    -0.11
     sebuah
    -0.09
     a
    -0.09
    ä¸ĢåĢĭ
    -0.08
     an
    -0.07
     someone
    -0.07
    someone
    -0.07
    buah
    -0.07
     een
    -0.07
    nemonic
    -0.07
    POSITIVE LOGITS
    że
    0.06
     history
    0.06
    FD
    0.06
    oc
    0.06
    ues
    0.06
    lic
    0.06
    ále
    0.06
    awe
    0.05
     dabei
    0.05
    fd
    0.05
    Activations Density 0.233%

    No Known Activations