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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74905
    Prev
    Next
    INDEX
    Explanations

    references to building or construction activities

    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
    ãģĹãĤĩ
    -0.08
    eling
    -0.08
    rud
    -0.07
    .sm
    -0.07
    enheim
    -0.07
    DECL
    -0.07
    اÛĮØ´
    -0.06
    ãĤªãĥª
    -0.06
    eil
    -0.06
    ague
    -0.06
    POSITIVE LOGITS
    ingo
    0.07
    une
    0.06
     around
    0.06
    agne
    0.06
    enza
    0.06
     ÙħÙĪاد
    0.06
    ond
    0.06
     materi
    0.06
    ilda
    0.06
     MATERIAL
    0.06
    Activations Density 0.012%

    No Known Activations