© 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. 39898
    Prev
    Next
    INDEX
    Explanations

    economic terms and phrases related to market dynamics and consequences

    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
     due
    -0.06
     arrog
    -0.06
    ono
    -0.06
    assoc
    -0.05
    /c
    -0.05
    berg
    -0.05
    morph
    -0.05
     erotische
    -0.05
     armed
    -0.05
     history
    -0.05
    POSITIVE LOGITS
    igel
    0.08
    orex
    0.07
     overall
    0.07
    overall
    0.07
    undy
    0.07
    IBUT
    0.07
    ì±Ħ
    0.07
    ór
    0.07
    .LookAndFeel
    0.07
    sville
    0.07
    Activations Density 0.025%

    No Known Activations