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. 44295
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their administrations

    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
    @js
    -0.07
    /mainwindow
    -0.07
    ازÙĩ
    -0.07
     Handy
    -0.07
    ubar
    -0.07
    Prime
    -0.06
    ardown
    -0.06
     billeder
    -0.06
    ibt
    -0.06
    hci
    -0.06
    POSITIVE LOGITS
     administration
    0.16
     Administration
    0.15
     White
    0.13
     admin
    0.13
     Justice
    0.12
     Admin
    0.12
     team
    0.11
     administr
    0.11
     Administr
    0.11
     adm
    0.10
    Activations Density 0.013%

    No Known Activations