© 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. 124950
    Prev
    Next
    INDEX
    Explanations

    sentences that mention the United States or reference notable U.S. policies and events

    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
    #:
    -0.07
    ãĤ¥
    -0.07
    _RESERVED
    -0.06
     ÑģкладÑĥ
    -0.06
    ạ
    -0.06
     EÅŁ
    -0.06
    oped
    -0.06
    .splitContainer
    -0.06
    èŤ
    -0.06
    steen
    -0.06
    POSITIVE LOGITS
    gow
    0.07
    LTE
    0.07
    zdy
    0.07
    /meta
    0.06
    íĿ¥
    0.06
    _tF
    0.06
    ãĤ¿ãĥ¼
    0.06
    -New
    0.06
    _tD
    0.06
    Span
    0.06
    Activations Density 0.018%

    No Known Activations