© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 120374
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "when" indicating temporal context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ekli
    -0.06
    ares
    -0.06
    rou
    -0.05
    ogany
    -0.05
    éĥ¨
    -0.05
    νοÏį
    -0.05
     ÙħÙĨÙĩ
    -0.05
    ctor
    -0.05
    ules
    -0.05
    unk
    -0.05
    POSITIVE LOGITS
     regarding
    0.11
     concerning
    0.11
     regards
    0.10
     regard
    0.09
    Regarding
    0.09
     dealing
    0.08
     respecto
    0.08
     konusu
    0.08
     vá»ģ
    0.08
     Regarding
    0.08
    Activations Density 0.009%

    No Known Activations