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. 5600
    Prev
    Next
    INDEX
    Explanations

    terms related to superannuation and retirement savings

    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
    abee
    -0.06
    gın
    -0.06
    ãĥ³ãĥĢ
    -0.06
    侯
    -0.06
     Auction
    -0.06
     Boeh
    -0.06
    repid
    -0.06
    ellers
    -0.06
    jing
    -0.06
    èŃľ
    -0.06
    POSITIVE LOGITS
     Contributions
    0.10
     contributions
    0.09
    ann
    0.08
     super
    0.07
    Contrib
    0.07
     scheme
    0.07
     Scheme
    0.07
     funds
    0.07
     Lump
    0.07
     Contrib
    0.07
    Activations Density 0.009%

    No Known Activations