© 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. 93474
    Prev
    Next
    INDEX
    Explanations

    elements related to navigation and interface components in web 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
    lej
    -0.07
     jÃŃ
    -0.07
    arus
    -0.07
     lez
    -0.07
    ÃĹ↵↵
    -0.07
    anou
    -0.07
    MemoryWarning
    -0.06
    éĻIJ
    -0.06
    xn
    -0.06
    iteli
    -0.06
    POSITIVE LOGITS
    agn
    0.07
    ogs
    0.07
    iat
    0.06
    abus
    0.06
    Region
    0.06
    illes
    0.06
    band
    0.06
    ault
    0.06
    yr
    0.06
    atten
    0.06
    Activations Density 0.001%

    No Known Activations