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

    Neuronpedia

    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. 128010
    Prev
    Next
    INDEX
    Explanations

    mentions of lawmakers and members of parliament

    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
    CHASE
    -0.07
    anja
    -0.07
    бÑĥ
    -0.07
    /bind
    -0.07
    chy
    -0.07
     Bind
    -0.07
    tü
    -0.07
    élé
    -0.07
    lav
    -0.07
    anou
    -0.07
    POSITIVE LOGITS
    ships
    0.07
    orum
    0.06
    hips
    0.06
    -elect
    0.06
     Uncomment
    0.06
     who
    0.06
    reesome
    0.06
     Commons
    0.06
     al
    0.06
    965
    0.06
    Activations Density 0.013%

    No Known Activations