© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126674
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic power dynamics and market control

    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
    ulos
    -0.09
    .Designer
    -0.08
    º
    -0.08
     creampie
    -0.07
    ìĽĥ
    -0.07
    ugo
    -0.07
    ChildIndex
    -0.07
    μÏĮ
    -0.07
    usta
    -0.07
    arently
    -0.07
    POSITIVE LOGITS
     either
    0.11
     perhaps
    0.10
     maybe
    0.10
     further
    0.10
     again
    0.10
     or
    0.09
     possibly
    0.09
     might
    0.08
     algún
    0.08
    either
    0.08
    Activations Density 0.029%

    No Known Activations