© 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. 74387
    Prev
    Next
    INDEX
    Explanations

    attributes and roles of academic professionals

    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
    omo
    -0.09
    ắt
    -0.08
    egend
    -0.07
    erne
    -0.07
    iene
    -0.07
    ifo
    -0.07
    orne
    -0.07
    ingo
    -0.07
    oves
    -0.07
    efa
    -0.07
    POSITIVE LOGITS
     affiliated
    0.07
    ìŀIJìĿ¸
    0.06
    rics
    0.06
     bik
    0.06
    970
    0.06
     Center
    0.06
     membership
    0.06
    mÃŃ
    0.06
     alternate
    0.06
    uzey
    0.06
    Activations Density 0.013%

    No Known Activations