© 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. 89329
    Prev
    Next
    INDEX
    Explanations

    statements regarding political actions and decisions related to invitations and state visits

    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
    atypes
    -0.07
    lsen
    -0.07
    oyo
    -0.06
    idla
    -0.06
    areth
    -0.06
    SUMER
    -0.06
    ailable
    -0.06
    jÃŃž
    -0.06
    roller
    -0.06
    ISC
    -0.06
    POSITIVE LOGITS
     protocol
    0.08
     attendance
    0.07
     Vis
    0.07
     invitation
    0.07
     Coord
    0.07
     coordination
    0.07
     slots
    0.07
     invite
    0.07
     inclusion
    0.07
     recipro
    0.07
    Activations Density 0.006%

    No Known Activations