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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5301
    Prev
    Next
    INDEX
    Explanations

    references to online gaming and related industry terms

    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
    ÑĢаÑĩ
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
     Sultan
    -0.07
    Startup
    -0.07
    ìĿµ
    -0.07
    nete
    -0.07
    ulen
    -0.07
    olet
    -0.07
    mlink
    -0.07
    æ
    -0.07
    POSITIVE LOGITS
     content
    0.09
     Operators
    0.09
     operator
    0.08
     Content
    0.08
     Operator
    0.07
     operators
    0.07
     platform
    0.07
    content
    0.07
     license
    0.07
    _content
    0.06
    Activations Density 0.003%

    No Known Activations