© 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. 87831
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transitions or milestones in a person's life

    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
    enne
    -0.06
    úc
    -0.06
    è
    -0.06
    ãģ¾ãģ¾
    -0.06
    isko
    -0.06
    ất
    -0.06
    едÑĮ
    -0.06
    анка
    -0.06
    ite
    -0.06
    ildren
    -0.06
    POSITIVE LOGITS
     finish
    0.08
    ward
    0.07
     completing
    0.07
     completion
    0.07
    tero
    0.07
     finishes
    0.07
     finishing
    0.07
     finished
    0.07
    WARE
    0.07
    thouse
    0.07
    Activations Density 0.016%

    No Known Activations