© 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. 79149
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and social disruption

    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
    etch
    -0.07
    ennen
    -0.07
    ocs
    -0.07
    å¯
    -0.07
    orary
    -0.06
    iew
    -0.06
    ambre
    -0.06
    StateManager
    -0.06
    _ET
    -0.06
    ocy
    -0.06
    POSITIVE LOGITS
     travel
    0.11
    travel
    0.10
     physical
    0.09
     Travel
    0.09
     visit
    0.09
     physically
    0.09
     Physical
    0.09
     traveled
    0.09
     traveling
    0.08
     normal
    0.08
    Activations Density 0.108%

    No Known Activations