© 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. 15-LLAMASCOPE-RES-131K
    11. 27296
    Prev
    Next
    INDEX
    Explanations

    references to various professional and literary associations and societies

    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
     Fleming
    -0.06
    ICES
    -0.06
     minist
    -0.06
     bay
    -0.06
    OUT
    -0.06
    iquid
    -0.06
    dad
    -0.06
    que
    -0.05
    ké
    -0.05
    colo
    -0.05
    POSITIVE LOGITS
    /state
    0.07
    /Foundation
    0.07
    "":
    0.07
    ilent
    0.07
    ÏĦÏħ
    0.07
     purch
    0.07
     Yönetim
    0.06
    ëıĦë¡ľ
    0.06
    ÃŃÅ¡
    0.06
    ustin
    0.06
    Activations Density 0.034%

    No Known Activations