© 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. 26203
    Prev
    Next
    INDEX
    Explanations

    the Spanish verb "espiar" (to spy) and seems to activate on English sentences containing a sequence of words indicating relationships or agency.

    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
    pushViewController
    -0.07
    engers
    -0.06
    ARSER
    -0.06
    .partner
    -0.06
    zers
    -0.06
    جاد
    -0.06
    oga
    -0.06
     Lever
    -0.06
    à¤Ĥà¤ľà¤¨
    -0.06
    λÏī
    -0.06
    POSITIVE LOGITS
     surveillance
    0.18
     monitoring
    0.17
    çĽij
    0.15
     monitor
    0.15
     spy
    0.15
     spying
    0.14
     Monitoring
    0.14
     surve
    0.14
    monitor
    0.14
     observation
    0.13
    Activations Density 0.019%

    No Known Activations