© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129182
    Prev
    Next
    INDEX
    Explanations

    references to loss and remembrance of individuals, specifically in the context of grief

    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
     célib
    -0.07
    лÑĥг
    -0.07
     ,↵↵
    -0.07
    puted
    -0.07
     tabi
    -0.07
    é¢Ĩ导
    -0.06
    ủ
    -0.06
    apult
    -0.06
    emploi
    -0.06
    /stretch
    -0.06
    POSITIVE LOGITS
    ies
    0.06
    {{{
    0.06
     ########.
    0.06
     etc
    0.06
    rud
    0.06
    ¶
    0.06
     tong
    0.05
    ower
    0.05
     Dahl
    0.05
    ecko
    0.05
    Activations Density 0.014%

    No Known Activations