© 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. 88345
    Prev
    Next
    INDEX
    Explanations

    keywords related to economics and employment trends

    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
    yles
    -0.07
    LOS
    -0.07
    alama
    -0.07
    enheim
    -0.07
    enny
    -0.06
    Äħd
    -0.06
     Meg
    -0.06
     freak
    -0.06
    iges
    -0.06
    alah
    -0.06
    POSITIVE LOGITS
    æĤŁ
    0.07
    omorphic
    0.06
    .scalablytyped
    0.06
    омина
    0.06
    εÏħ
    0.06
    stery
    0.05
    aliz
    0.05
     ÑĤов
    0.05
    emploi
    0.05
    inear
    0.05
    Activations Density 0.029%

    No Known Activations