© 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. 17107
    Prev
    Next
    INDEX
    Explanations

    terms related to data backup and recovery processes

    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
    íĮ
    -0.07
    زار
    -0.07
    greens
    -0.07
    بÙĬÙĨ
    -0.07
    uga
    -0.07
     yüz
    -0.07
    aden
    -0.06
     trá»ĭ
    -0.06
    ãĥ¡ãĥ©
    -0.06
    annies
    -0.06
    POSITIVE LOGITS
     backup
    0.15
    backup
    0.13
     Backup
    0.13
    å¤ĩ份
    0.12
     backups
    0.12
    Backup
    0.12
    .backup
    0.12
     backed
    0.11
    _backup
    0.11
    ä¿ĿåŃĺ
    0.11
    Activations Density 0.031%

    No Known Activations