© 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 EvalsExportsinterp-engineNEWAPI 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. 72564
    Prev
    Next
    INDEX
    Explanations

    references to economic metrics and financial data

    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
    egt
    -0.08
    ifen
    -0.08
    seau
    -0.08
    õi
    -0.07
    alla
    -0.07
    eyim
    -0.07
     تط
    -0.07
    té
    -0.07
    afari
    -0.07
    _defaults
    -0.07
    POSITIVE LOGITS
     labor
    0.07
     invis
    0.06
     union
    0.06
     families
    0.06
     Buff
    0.06
     low
    0.06
    Aggregate
    0.06
     labour
    0.06
     recovery
    0.06
     America
    0.06
    Activations Density 0.039%

    No Known Activations