© 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. 60512
    Prev
    Next
    INDEX
    Explanations

    code related to user authentication and access management

    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
    bsub
    -0.07
     eiusmod
    -0.07
    ARGET
    -0.07
    rost
    -0.07
    uebas
    -0.06
    ï½¥
    -0.06
     chứng
    -0.06
    uth
    -0.06
    TestClass
    -0.06
    branch
    -0.06
    POSITIVE LOGITS
    iddet
    0.06
    ndx
    0.06
    sts
    0.06
     Union
    0.05
    ourcing
    0.05
     Tabs
    0.05
    ãĤıãĤĬ
    0.05
     huku
    0.05
     trained
    0.05
     McCoy
    0.05
    Activations Density 0.014%

    No Known Activations