Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11529
    Prev
    Next
    INDEX
    Explanations

    phrases related to user experience and engagement on websites

    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
    itchen
    -0.07
    unci
    -0.06
    ÑĢоз
    -0.06
    PIO
    -0.06
    ÏĩÏĮ
    -0.06
    çĩ
    -0.06
    ÑĮко
    -0.06
    ÑĢÑĥÑĪ
    -0.05
    amework
    -0.05
    å¡
    -0.05
    POSITIVE LOGITS
     browsing
    0.18
     navigation
    0.16
     browser
    0.16
     browsers
    0.15
     surfing
    0.15
     clicking
    0.15
     navig
    0.15
     clicks
    0.14
     naveg
    0.14
     brows
    0.14
    Activations Density 0.039%

    No Known Activations