© 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. 90741
    Prev
    Next
    INDEX
    Explanations

    occurrences of authority or hierarchical structures and their actions

    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
    ارج
    -0.07
    جار
    -0.07
    istrovstvÃŃ
    -0.07
    lÃŃÄį
    -0.07
    اسÛĮ
    -0.07
    xies
    -0.07
    itchens
    -0.06
    yen
    -0.06
    _irq
    -0.06
     frau
    -0.06
    POSITIVE LOGITS
     altogether
    0.10
     khá»ıi
    0.08
    iform
    0.07
    andin
    0.07
    ertos
    0.06
     grips
    0.06
     anymore
    0.06
     consideration
    0.06
    fer
    0.06
    ä»ķ
    0.06
    Activations Density 0.035%

    No Known Activations