© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126558
    Prev
    Next
    INDEX
    Explanations

    instances of governmental announcements or political actions

    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
     hookers
    -0.09
    ζα
    -0.08
     dán
    -0.08
    LEGRO
    -0.08
    .addProperty
    -0.07
    ruptcy
    -0.07
     patriot
    -0.07
     Buccaneers
    -0.07
    -ip
    -0.07
     SKF
    -0.07
    POSITIVE LOGITS
     Pes
    0.08
     weather
    0.06
     President
    0.06
     flash
    0.06
     worldwide
    0.06
     US
    0.06
     Earth
    0.06
     London
    0.06
     Pope
    0.06
     world
    0.06
    Activations Density 0.035%

    No Known Activations