© 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. 83691
    Prev
    Next
    INDEX
    Explanations

    concepts related to social structures and dynamics

    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
    zend
    -0.06
    wich
    -0.06
    ones
    -0.06
    yd
    -0.06
    rone
    -0.06
    oner
    -0.06
    yc
    -0.05
     compuls
    -0.05
    933
    -0.05
    his
    -0.05
    POSITIVE LOGITS
    /includes
    0.07
    SetActive
    0.07
    qli
    0.07
    ÃĸL
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    ãĥ³ãĥģ
    0.07
    -transitional
    0.06
    ideos
    0.06
    าห
    0.06
    olver
    0.06
    Activations Density 0.039%

    No Known Activations