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. 43433
    Prev
    Next
    INDEX
    Explanations

    elements related to affordability and pricing in travel or accommodations

    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
    ~
    -0.08
     Mey
    -0.06
    ~↵
    -0.06
     â̦↵↵
    -0.06
    unik
    -0.06
    ç³»
    -0.06
    /download
    -0.06
    ~↵↵
    -0.05
     Dwight
    -0.05
    ÏģÏį
    -0.05
    POSITIVE LOGITS
    享
    0.06
    оло
    0.06
    çĭIJ
    0.06
    ').'
    0.06
     elegance
    0.06
    æµľ
    0.06
    _intf
    0.06
    ÄĻd
    0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.06
    azzi
    0.06
    Activations Density 0.006%

    No Known Activations