© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15074
    Prev
    Next
    INDEX
    Explanations

    mentions of issues related to notifications and their functionality

    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
    Modifiers
    -0.08
    ovit
    -0.07
    ohon
    -0.07
    raki
    -0.07
    echn
    -0.07
    лоÑĩ
    -0.07
    .instructions
    -0.07
    ritel
    -0.07
     mailing
    -0.07
    aptops
    -0.07
    POSITIVE LOGITS
     notification
    0.07
    aster
    0.06
     notifications
    0.06
    asts
    0.06
     Notification
    0.06
     dismissal
    0.06
     reception
    0.06
     pop
    0.06
     Notifications
    0.06
     Broadway
    0.06
    Activations Density 0.019%

    No Known Activations