© 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. 119098
    Prev
    Next
    INDEX
    Explanations

    elements related to layout measurement in Android development

    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
    plib
    -0.07
    engo
    -0.07
    stantiate
    -0.06
     Wasser
    -0.06
     mold
    -0.06
    Ïģα
    -0.06
    engin
    -0.06
    indr
    -0.06
    PARSE
    -0.06
    ÙĦ
    -0.06
    POSITIVE LOGITS
    WithValue
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    URRED
    0.07
    976
    0.07
     NSObject
    0.06
    UED
    0.06
    'gc
    0.06
    871
    0.06
    Ī
    0.06
    EventArgs
    0.06
    Activations Density 0.001%

    No Known Activations