© 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. 93410
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and forming groups

    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
    aret
    -0.07
    ë²Į
    -0.07
    quent
    -0.07
    obi
    -0.07
    agoon
    -0.06
    èĬ
    -0.06
    sburgh
    -0.06
    lap
    -0.06
    quam
    -0.06
    arde
    -0.06
    POSITIVE LOGITS
    oard
    0.07
    579
    0.06
     triple
    0.06
     Triple
    0.06
     Legend
    0.06
     TResult
    0.06
    naz
    0.06
    ãĤ¹ãĤ¯
    0.06
    eton
    0.06
     triangle
    0.06
    Activations Density 0.001%

    No Known Activations