© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84822
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and control in societal structures

    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
    ics
    -0.07
    abin
    -0.06
    gn
    -0.06
    æĨ
    -0.06
    iscal
    -0.06
    etti
    -0.06
    ulo
    -0.06
    otes
    -0.06
    icas
    -0.06
     Diesel
    -0.06
    POSITIVE LOGITS
    /control
    0.08
    eer
    0.08
     affairs
    0.08
     resources
    0.08
     destin
    0.07
     destiny
    0.07
     access
    0.07
     disproportion
    0.07
    ej
    0.07
    (control
    0.07
    Activations Density 0.026%

    No Known Activations