© 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. 83448
    Prev
    Next
    INDEX
    Explanations

    technical references to code lines and measurements related to UI components 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
    .simps
    -0.08
    engin
    -0.08
    ÙĦاÙħ
    -0.07
    æŁĦ
    -0.07
    Äįen
    -0.07
    Longrightarrow
    -0.07
    vala
    -0.07
    keit
    -0.07
    omas
    -0.07
    ensem
    -0.07
    POSITIVE LOGITS
     RU
    0.07
     ru
    0.06
     Estates
    0.05
    opp
    0.05
    eya
    0.05
    anja
    0.05
    pled
    0.05
    ERP
    0.05
     pled
    0.05
     Depths
    0.05
    Activations Density 0.001%

    No Known Activations