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. 22-LLAMASCOPE-RES-131K
    6. 5622
    Prev
    Next
    INDEX
    Explanations

    references to Arabian-themed travel and tourism events

    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
    ãģĬãĤĬ
    -0.07
    indow
    -0.07
    gui
    -0.07
    cak
    -0.07
    akin
    -0.06
    gia
    -0.06
    639
    -0.06
    olon
    -0.06
    ile
    -0.06
     repl
    -0.06
    POSITIVE LOGITS
     Peninsula
    0.12
     peninsula
    0.09
     Gulf
    0.09
     Nights
    0.09
     Sea
    0.08
    Sea
    0.08
     Seas
    0.07
     Penis
    0.07
    _exports
    0.07
    _pen
    0.06
    Activations Density 0.002%

    No Known Activations