© 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. 5-LLAMASCOPE-RES-131K
    11. 126912
    Prev
    Next
    INDEX
    Explanations

    terms associated with data reception and transmission in a network context

    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
    phe
    -0.07
    artz
    -0.07
    entic
    -0.07
    urch
    -0.07
    ange
    -0.06
    qv
    -0.06
    gram
    -0.06
    teri
    -0.06
     themselves
    -0.06
    illary
    -0.06
    POSITIVE LOGITS
    až
    0.08
    ables
    0.08
    oji
    0.07
    Merit
    0.07
    uhan
    0.07
    å¼ı
    0.07
    edImage
    0.07
    èŁ
    0.07
    IVES
    0.07
    åħ¼
    0.07
    Activations Density 0.013%

    No Known Activations