© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128183
    Prev
    Next
    INDEX
    Explanations

    concepts related to balance and stability in complex systems

    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
    imet
    -0.07
    logan
    -0.06
     poil
    -0.06
     ami
    -0.06
    vou
    -0.06
     AIDS
    -0.06
    usan
    -0.06
    .XR
    -0.06
    oran
    -0.06
     aren
    -0.06
    POSITIVE LOGITS
    LOAT
    0.08
    Ìĥ
    0.07
    FFF
    0.07
     Blo
    0.07
    peater
    0.06
    Blo
    0.06
    баÑĩ
    0.06
     Ki
    0.06
    çŃĭ
    0.06
    ctrl
    0.06
    Activations Density 0.002%

    No Known Activations