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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84765
    Prev
    Next
    INDEX
    Explanations

    professional titles and roles related to healthcare and research 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
    ách
    -0.07
    asa
    -0.07
    antor
    -0.07
    зи
    -0.06
    ầm
    -0.06
    assa
    -0.06
    orsi
    -0.06
    جÛĮ
    -0.06
    KeyEvent
    -0.06
    /packages
    -0.06
    POSITIVE LOGITS
     Chronicles
    0.07
    (Common
    0.07
    (C
    0.07
    uttle
    0.06
    ellation
    0.06
    912
    0.06
     Stateless
    0.06
    =c
    0.06
    (CL
    0.06
    ISR
    0.06
    Activations Density 1.998%

    No Known Activations