© 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. 900
    Prev
    Next
    INDEX
    Explanations

    terms related to professional careers and roles across various fields

    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
    elize
    -0.07
    eref
    -0.07
    stein
    -0.07
    ements
    -0.07
    ÑĢой
    -0.07
    iones
    -0.07
    atten
    -0.06
    venes
    -0.06
    çīĮ
    -0.06
    ÑģÑĤвоÑĢ
    -0.06
    POSITIVE LOGITS
     career
    0.08
     experience
    0.07
     life
    0.07
    ovan
    0.07
    yna
    0.06
     Garrison
    0.06
    ahy
    0.06
    ãĥ¥ãĥ¼
    0.06
     history
    0.06
    ContentSize
    0.06
    Activations Density 0.018%

    No Known Activations