© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77548
    Prev
    Next
    INDEX
    Explanations

    design-related terms and concepts, particularly those associated with pattern and background design

    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
    aller
    -0.07
    åı£
    -0.06
     citizen
    -0.06
    odont
    -0.06
     Citizen
    -0.06
    hood
    -0.06
    bookmark
    -0.06
    odon
    -0.06
    наÑĢод
    -0.05
    164
    -0.05
    POSITIVE LOGITS
     background
    0.13
     backgrounds
    0.12
    background
    0.11
    èĥĮæĻ¯
    0.11
    -background
    0.11
     Background
    0.11
    Background
    0.10
    .background
    0.10
     bg
    0.09
    (background
    0.09
    Activations Density 0.015%

    No Known Activations