© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55570
    Prev
    Next
    INDEX
    Explanations

    themes related to remembrance and memorializing deceased individuals

    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
    dete
    -0.07
    á»įt
    -0.07
    ViewState
    -0.07
    ekl
    -0.07
     нал
    -0.07
    enez
    -0.07
    ầu
    -0.07
    loo
    -0.07
    entifier
    -0.07
     å¹³æĸ¹
    -0.07
    POSITIVE LOGITS
     whose
    0.09
     past
    0.08
     departed
    0.08
     lost
    0.08
     gone
    0.08
     loved
    0.07
     depart
    0.07
     whom
    0.07
     losses
    0.07
    chie
    0.07
    Activations Density 0.015%

    No Known Activations