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. 5728
    Prev
    Next
    INDEX
    Explanations

    references to governmental or political processes

    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
    ijken
    -0.07
     Felix
    -0.07
    flt
    -0.07
    acro
    -0.06
    fleet
    -0.06
     fel
    -0.06
    alous
    -0.06
    istrov
    -0.06
    appable
    -0.06
    \grid
    -0.06
    POSITIVE LOGITS
     senators
    0.07
    ahn
    0.07
     bills
    0.07
     Wolff
    0.06
    iele
    0.06
    Motion
    0.06
    Senator
    0.06
    vÄĽt
    0.06
     bill
    0.06
    ê°ľ
    0.06
    Activations Density 0.011%

    No Known Activations