© 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. 127107
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States

    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
    terra
    -0.07
    endale
    -0.07
    wert
    -0.07
    slaught
    -0.07
    /INFO
    -0.06
    aye
    -0.06
     Pru
    -0.06
    ITIVE
    -0.06
    inç
    -0.06
    iffin
    -0.06
    POSITIVE LOGITS
    lings
    0.07
     Senator
    0.07
    acle
    0.06
    fully
    0.06
    oyo
    0.06
     senator
    0.06
    ÑĭÑĤ
    0.06
     blank
    0.06
    ÏģÏİ
    0.06
    urre
    0.06
    Activations Density 0.011%

    No Known Activations