© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28921
    Prev
    Next
    INDEX
    Explanations

    references to the impact of the COVID-19 pandemic on society and the economy

    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
    asive
    -0.07
    :"-"`↵
    -0.07
    á»ĩ
    -0.06
    ÚĺÙĩ
    -0.06
    IDER
    -0.06
     Refriger
    -0.06
    ÑĢежд
    -0.06
     zorun
    -0.06
    ÑĢиÑģÑĤи
    -0.06
    YLON
    -0.06
    POSITIVE LOGITS
     gradual
    0.10
     gradually
    0.10
     finally
    0.09
    æģ¢
    0.09
     easing
    0.09
    itore
    0.09
     normalization
    0.09
     improvement
    0.09
     normal
    0.09
     Grad
    0.09
    Activations Density 0.212%

    No Known Activations