© 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. 15-LLAMASCOPE-RES-131K
    6. 62244
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences related to inquiries and concerns raised in a social or legal context

    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
    ceed
    -0.06
    461
    -0.06
    ire
    -0.06
    ubes
    -0.06
    arge
    -0.06
    oss
    -0.06
    .rev
    -0.06
    aptors
    -0.06
    θÏħ
    -0.05
    imat
    -0.05
    POSITIVE LOGITS
    \Doctrine
    0.07
    insky
    0.07
    chl
    0.07
    /datatables
    0.06
    nict
    0.06
    onus
    0.06
    Codes
    0.06
    راÙĨÙĩ
    0.06
     {{--<
    0.06
    erdem
    0.06
    Activations Density 0.010%

    No Known Activations