© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129338
    Prev
    Next
    INDEX
    Explanations

    references to tourism and travel events in the Middle East

    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
    _trampoline
    -0.07
    몬
    -0.07
    anje
    -0.07
     bow
    -0.06
    arta
    -0.06
    980
    -0.06
    .constraint
    -0.06
    atron
    -0.06
     Nguyên
    -0.06
    ÑģÑĤÑĢÑĥменÑĤ
    -0.06
    POSITIVE LOGITS
     Awards
    0.08
     awards
    0.08
     Award
    0.07
     Nom
    0.07
     award
    0.07
     Pey
    0.06
    gon
    0.06
     Hotel
    0.06
     property
    0.06
     Property
    0.06
    Activations Density 0.001%

    No Known Activations