© 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. 61862
    Prev
    Next
    INDEX
    Explanations

    references to emotional well-being and personal development

    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
    imbus
    -0.08
    izo
    -0.08
    éĽĦ
    -0.07
    allon
    -0.07
    ứng
    -0.07
     Strait
    -0.07
    INCT
    -0.07
    OGLE
    -0.07
    ãģ¤ãģ¶
    -0.07
    undry
    -0.07
    POSITIVE LOGITS
     themselves
    0.06
     loro
    0.06
     prod
    0.06
     their
    0.05
     coax
    0.05
    Ŀ
    0.05
    δά
    0.05
    dataProvider
    0.05
     they
    0.05
     They
    0.05
    Activations Density 0.033%

    No Known Activations