© 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. 105725
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements and upcoming events

    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
    boom
    -0.07
    amage
    -0.06
    /es
    -0.06
     prelim
    -0.06
    erties
    -0.06
    icals
    -0.06
    Sizer
    -0.05
    ×IJ
    -0.05
    owie
    -0.05
     Hutch
    -0.05
    POSITIVE LOGITS
    hti
    0.08
    _ipc
    0.08
     soon
    0.07
     announcement
    0.07
    avax
    0.07
    tran
    0.07
    cheon
    0.07
    ulumi
    0.07
    dale
    0.07
     Announcement
    0.07
    Activations Density 0.012%

    No Known Activations