© 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. 28217
    Prev
    Next
    INDEX
    Explanations

    the word "subject" and very slightly activates around "matter"

    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
    ushing
    -0.07
    ouro
    -0.07
    ue
    -0.07
     Sabha
    -0.07
    ersions
    -0.07
    ä¸Ŀ
    -0.07
    ersh
    -0.07
    ozo
    -0.07
    ock
    -0.06
    /preferences
    -0.06
    POSITIVE LOGITS
    ively
    0.15
    ivity
    0.14
     matter
    0.13
    ivities
    0.12
    matter
    0.12
     Matter
    0.11
    ive
    0.10
    ivism
    0.10
    ivist
    0.09
    IVE
    0.07
    Activations Density 0.008%

    No Known Activations