© 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. 119309
    Prev
    Next
    INDEX
    Explanations

    elements related to family activities and enjoyment during outings

    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
    .tpl
    -0.07
    field
    -0.06
    iswa
    -0.06
    archive
    -0.06
    DOG
    -0.06
    ระ
    -0.06
    andy
    -0.06
     PSA
    -0.06
     insp
    -0.06
    ummer
    -0.06
    POSITIVE LOGITS
     Meer
    0.07
    \Doctrine
    0.07
     Dit
    0.06
     Hours
    0.06
    itect
    0.06
    èį·
    0.06
     tickets
    0.06
    iment
    0.06
    emek
    0.06
    queues
    0.06
    Activations Density 0.002%

    No Known Activations