© 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. 57365
    Prev
    Next
    INDEX
    Explanations

    concepts related to creation and dynamics of power 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
    unas
    -0.06
     Gaz
    -0.06
     stuff
    -0.06
    λÏİ
    -0.06
    140
    -0.06
     minh
    -0.06
    AppState
    -0.06
     ultr
    -0.06
     Domino
    -0.06
    ãĥĨãĥ«
    -0.05
    POSITIVE LOGITS
    othy
    0.08
     ΣεÏĢ
    0.07
    iface
    0.07
    ازÙĦ
    0.07
    verty
    0.06
    ameda
    0.06
    _PRIVATE
    0.06
     phá»iji
    0.06
    maal
    0.06
    istle
    0.06
    Activations Density 0.000%

    No Known Activations