© 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. 59241
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizational and systemic structures 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
    afx
    -0.08
    ietet
    -0.08
    :UIAlert
    -0.07
    dsp
    -0.07
    UGIN
    -0.07
    antro
    -0.07
    pedia
    -0.07
    isman
    -0.07
    upal
    -0.07
    .jupiter
    -0.07
    POSITIVE LOGITS
     Dep
    0.07
     Initiative
    0.07
     DataBase
    0.07
     Markup
    0.07
    orum
    0.06
    staking
    0.06
     Institute
    0.06
     Mart
    0.06
     Herman
    0.06
     sadd
    0.06
    Activations Density 0.086%

    No Known Activations