© 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. 26156
    Prev
    Next
    INDEX
    Explanations

    a bit hard to describe so I will provide several options:Option 1: the neuron seems to activate when "in" and "ians" occur close together, but this is not the only trigger.Option 2: the neuron seems to activate around parts of conversation between the assistant and

    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
    mÃŃ
    -0.07
    otime
    -0.07
    ometr
    -0.07
    urrenc
    -0.06
    urette
    -0.06
    Verified
    -0.06
    .TypeOf
    -0.06
    >\<^
    -0.06
    adera
    -0.06
    ITIZE
    -0.06
    POSITIVE LOGITS
    ters
    0.06
    ¾
    0.06
    .ToShort
    0.06
    adge
    0.06
    ly
    0.06
    e
    0.06
    aly
    0.06
    ields
    0.06
    able
    0.06
    -number
    0.06
    Activations Density 0.073%

    No Known Activations