© 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. 77184
    Prev
    Next
    INDEX
    Explanations

    a specific cultural or regional context, particularly related to children and play

    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
     Nack
    -0.08
    torrent
    -0.07
     Friendship
    -0.07
    .ca
    -0.07
    ALLOW
    -0.06
    OLEAN
    -0.06
    ContentView
    -0.06
    ierce
    -0.06
    otte
    -0.06
    ÅĽnie
    -0.06
    POSITIVE LOGITS
    æĹı
    0.06
     sacred
    0.06
     Listing
    0.06
     Os
    0.06
     Hin
    0.06
     tua
    0.06
    027
    0.05
     listing
    0.05
     surface
    0.05
     Sacred
    0.05
    Activations Density 0.009%

    No Known Activations