© 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. 107914
    Prev
    Next
    INDEX
    Explanations

    keywords related to smart home technology and energy efficiency

    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
     for
    -0.06
    ors
    -0.06
     force
    -0.06
    ette
    -0.06
     Arb
    -0.06
     bump
    -0.06
     rib
    -0.06
    -0.06
     past
    -0.06
    um
    -0.06
    POSITIVE LOGITS
    remote
    0.09
     remote
    0.09
    éģł
    0.09
    è¿ľ
    0.09
    Remote
    0.08
     distant
    0.08
     Remote
    0.08
    oyer
    0.08
    commands
    0.08
     æĻ
    0.08
    Activations Density 0.012%

    No Known Activations