© 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. 15-LLAMASCOPE-RES-131K
    11. 90866
    Prev
    Next
    INDEX
    Explanations

    phrases discussing methods and modes of action or administration in various contexts

    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
    leich
    -0.07
     éº
    -0.06
    onga
    -0.06
    ogui
    -0.06
    .until
    -0.06
    iliz
    -0.06
    eat
    -0.06
    idge
    -0.06
    ibia
    -0.06
    ëŀĢ
    -0.06
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.07
     approach
    0.07
     modes
    0.07
    Modes
    0.06
     way
    0.06
    rome
    0.06
     tuyến
    0.06
    appro
    0.06
     Approach
    0.06
     Modes
    0.06
    Activations Density 0.029%

    No Known Activations