© 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. 77144
    Prev
    Next
    INDEX
    Explanations

    terms related to energy production and consumption

    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
    wide
    -0.07
    otes
    -0.06
    uses
    -0.06
    469
    -0.06
    at
    -0.06
    with
    -0.06
    ui
    -0.06
    1
    -0.06
    _
    -0.06
    -0.06
    POSITIVE LOGITS
    gamber
    0.08
    OURCE
    0.08
    éĺħ读次æķ°
    0.08
     ChÃŃ
    0.08
    bron
    0.08
    Intialized
    0.08
    Äįet
    0.08
    hiba
    0.08
    ERSHEY
    0.07
    /weather
    0.07
    Activations Density 0.050%

    No Known Activations