© 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. 15-LLAMASCOPE-RES-131K
    11. 89617
    Prev
    Next
    INDEX
    Explanations

    terms related to management and societal responsibility

    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
    rita
    -0.07
    iy
    -0.07
    iš
    -0.07
     bóng
    -0.07
     Terrain
    -0.06
    endar
    -0.06
    uga
    -0.06
    /cop
    -0.06
    ãģĴ
    -0.06
    onica
    -0.06
    POSITIVE LOGITS
     каÑģ
    0.08
    -style
    0.07
    iglia
    0.07
    ìłĢ
    0.07
     prem
    0.07
     aspect
    0.07
    icone
    0.06
    breadcrumb
    0.06
     Hatch
    0.06
     skills
    0.06
    Activations Density 0.032%

    No Known Activations