© 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. 15-LLAMASCOPE-RES-131K
    11. 26855
    Prev
    Next
    INDEX
    Explanations

    terms related to family support in the context of mental health

    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
    sko
    -0.07
     trúc
    -0.07
    IDD
    -0.07
    ensis
    -0.07
    _categorical
    -0.07
    oui
    -0.07
    lacak
    -0.07
    legen
    -0.07
     пÑĢоÑĪ
    -0.06
    ạo
    -0.06
    POSITIVE LOGITS
    978
    0.08
     support
    0.07
     loved
    0.07
     supportive
    0.06
    /support
    0.06
     Support
    0.06
     themselves
    0.06
     indirect
    0.06
    ivor
    0.06
     shares
    0.06
    Activations Density 0.013%

    No Known Activations