© 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 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. 130756
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to mechanical and electrical services

    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
    uiltin
    -0.07
    /compiler
    -0.07
    precated
    -0.07
    ÑģеÑĢ
    -0.07
    ptom
    -0.07
    αιν
    -0.07
    OffsetTable
    -0.07
    braco
    -0.07
    jax
    -0.07
    heim
    -0.07
    POSITIVE LOGITS
     custom
    0.07
     complete
    0.07
     Corporate
    0.07
     accompany
    0.07
     corporate
    0.07
    complete
    0.07
     Custom
    0.06
     companion
    0.06
     Ghost
    0.06
     special
    0.06
    Activations Density 0.037%

    No Known Activations