© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128393
    Prev
    Next
    INDEX
    Explanations

    phrases related to network security and access setup

    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
    anas
    -0.06
    amm
    -0.06
    eeper
    -0.05
    des
    -0.05
    ertools
    -0.05
    åIJ¹
    -0.05
    Launcher
    -0.05
     sl
    -0.05
     appointment
    -0.05
     import
    -0.05
    POSITIVE LOGITS
    ç¹Ķ
    0.07
    .mob
    0.07
    Bonjour
    0.07
    SSID
    0.07
    Outdoor
    0.06
    Ỽp
    0.06
    ÑĢеÑĪ
    0.06
     Mesh
    0.06
    _ctl
    0.06
    oha
    0.06
    Activations Density 0.018%

    No Known Activations