© 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. 30018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating enjoyment or positive experiences

    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
    adu
    -0.07
    .Library
    -0.07
    .opensource
    -0.06
    ãĥ³ãĥ
    -0.06
    úsqueda
    -0.06
    ocy
    -0.06
    naires
    -0.06
    ept
    -0.06
    sled
    -0.06
    terdam
    -0.06
    POSITIVE LOGITS
     freedoms
    0.08
     success
    0.08
     freedom
    0.08
     succès
    0.08
    ably
    0.07
    enville
    0.07
    iji
    0.06
     status
    0.06
    gos
    0.06
     economies
    0.06
    Activations Density 0.013%

    No Known Activations