© 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. 15-LLAMASCOPE-RES-131K
    11. 86507
    Prev
    Next
    INDEX
    Explanations

    mentions of networks and connectivity within urban or natural environments

    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
    anton
    -0.06
     Lens
    -0.06
     Hicks
    -0.06
    /WebAPI
    -0.06
     wizard
    -0.06
    azeera
    -0.06
    AFX
    -0.06
    æ¡£
    -0.06
    ifter
    -0.06
     housed
    -0.05
    POSITIVE LOGITS
     network
    0.13
    -network
    0.11
     networks
    0.11
    _network
    0.11
    network
    0.11
     Network
    0.10
    etwork
    0.10
     شبکÙĩ
    0.09
     меÑĢеж
    0.09
    ç½ij绾
    0.09
    Activations Density 0.087%

    No Known Activations