© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59579
    Prev
    Next
    INDEX
    Explanations

    phrases involving the act of playing or engaging in activities with others

    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
    еди
    -0.08
    ayan
    -0.07
    ovel
    -0.06
    .Err
    -0.06
    hya
    -0.06
    wal
    -0.06
    ãģİ
    -0.06
    fet
    -0.06
    tr
    -0.06
    olia
    -0.06
    POSITIVE LOGITS
     Pocket
    0.06
    ibold
    0.06
     @"↵
    0.06
    odel
    0.06
    립
    0.06
     ç²
    0.06
     ActiveForm
    0.06
    anco
    0.06
    .pretty
    0.06
     evidenced
    0.06
    Activations Density 0.012%

    No Known Activations