© 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. 127040
    Prev
    Next
    INDEX
    Explanations

    terms related to branding and design elements

    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
    skirts
    -0.08
    aylight
    -0.08
    rchive
    -0.08
    amework
    -0.07
    ptom
    -0.07
    stro
    -0.07
    .opensource
    -0.07
    DataExchange
    -0.07
    technology
    -0.07
    ALLERY
    -0.07
    POSITIVE LOGITS
     design
    0.09
     logo
    0.09
    /logo
    0.09
     designs
    0.08
     branding
    0.08
     Logo
    0.07
    design
    0.07
     brand
    0.07
    opak
    0.07
     Design
    0.07
    Activations Density 0.025%

    No Known Activations