© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126135
    Prev
    Next
    INDEX
    Explanations

    references to legal professionals and law-related terms

    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
     indeb
    -0.07
     attachments
    -0.06
    ",__
    -0.06
    кÑĥÑĢ
    -0.06
    rawn
    -0.06
    attachments
    -0.06
    parate
    -0.06
     nét
    -0.06
     paran
    -0.06
    igate
    -0.06
    POSITIVE LOGITS
    -directory
    0.06
     rencontrer
    0.06
     Directory
    0.06
    ysa
    0.06
    uggage
    0.06
    holm
    0.06
    .special
    0.06
     ÐĿаз
    0.06
    èĨ
    0.06
    hir
    0.06
    Activations Density 0.006%

    No Known Activations