© 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. 120033
    Prev
    Next
    INDEX
    Explanations

    references to foreign investment and international financial interactions

    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
    ãĥĥãĤ°
    -0.06
    woff
    -0.06
    ÑĤин
    -0.06
    ennen
    -0.06
    ãĥ³ãĤ¿
    -0.06
    tep
    -0.06
    enez
    -0.06
    gings
    -0.06
    urst
    -0.06
    ouri
    -0.06
    POSITIVE LOGITS
     visitors
    0.07
    каÑģ
    0.07
     presence
    0.07
    /exp
    0.07
    oins
    0.06
    -backed
    0.06
    alion
    0.06
    TEE
    0.06
     visiting
    0.06
     germ
    0.06
    Activations Density 0.019%

    No Known Activations