© 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. 29376
    Prev
    Next
    INDEX
    Explanations

    topics related to global trade and economics

    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
    adol
    -0.07
    immer
    -0.07
    adal
    -0.07
    legg
    -0.07
    aram
    -0.06
    allas
    -0.06
    lama
    -0.06
    ardon
    -0.06
    izzle
    -0.06
    ittel
    -0.06
    POSITIVE LOGITS
    .ObjectModel
    0.07
     Tavern
    0.07
     Twice
    0.06
    Keywords
    0.06
     ÑģÑĤаÑĤÑĤÑĸ
    0.06
    ãĥĨãĥ«
    0.06
    Article
    0.06
     wings
    0.06
    ForKey
    0.06
    bor
    0.06
    Activations Density 0.055%

    No Known Activations