© 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. 119342
    Prev
    Next
    INDEX
    Explanations

    concepts related to control, authority, and institutions in society

    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
    rait
    -0.07
    idden
    -0.06
    ÑĢаÑħов
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    nota
    -0.06
    usk
    -0.06
    uber
    -0.06
    ç
    -0.06
    ushman
    -0.06
    angle
    -0.06
    POSITIVE LOGITS
     control
    0.09
     destiny
    0.09
     Control
    0.08
     affairs
    0.08
    -control
    0.08
    control
    0.08
    apia
    0.08
     controls
    0.07
     proceedings
    0.07
    /control
    0.07
    Activations Density 0.045%

    No Known Activations