© 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 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. 16476
    Prev
    Next
    INDEX
    Explanations

    references to emotional experiences related to loss and grieving

    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
    enti
    -0.07
    Menus
    -0.06
    LOCKS
    -0.06
    _Construct
    -0.06
    ä¼ij
    -0.06
    oru
    -0.06
     oprav
    -0.06
    _errno
    -0.06
    epad
    -0.06
    аÑĤкÑĥ
    -0.06
    POSITIVE LOGITS
     stuff
    0.10
     storage
    0.10
     contents
    0.10
     Storage
    0.09
     items
    0.09
    storage
    0.09
     Contents
    0.09
    Stuff
    0.09
     Stuff
    0.08
     Items
    0.08
    Activations Density 0.036%

    No Known Activations