© 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. 9-LLAMASCOPE-RES-131K
    11. 96312
    Prev
    Next
    INDEX
    Explanations

    references to "the world" and global contexts

    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
    اÙĦÙĦÙĩ
    -0.06
    seau
    -0.06
    635
    -0.06
     Unauthorized
    -0.06
    omba
    -0.06
     Hayes
    -0.05
     unsupported
    -0.05
     Swords
    -0.05
    ç½®
    -0.05
     Investors
    -0.05
    POSITIVE LOGITS
    /world
    0.08
    æĨ
    0.07
    opensource
    0.07
    nos
    0.07
    /Dk
    0.07
    YPRE
    0.07
    HeaderCode
    0.07
    SCO
    0.07
    rug
    0.07
    ecer
    0.06
    Activations Density 0.011%

    No Known Activations