© 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. 127473
    Prev
    Next
    INDEX
    Explanations

    phrases indicating growth or achievement of prominence in various fields or sectors

    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
     almost
    -0.09
     nearly
    -0.08
     often
    -0.07
    åĽº
    -0.07
     since
    -0.06
    sis
    -0.06
    à¤ī
    -0.06
     directly
    -0.06
    ickey
    -0.06
    almost
    -0.06
    POSITIVE LOGITS
    ylan
    0.09
     someday
    0.08
    pole
    0.07
    Eventually
    0.07
     Eventually
    0.07
    pires
    0.07
     اختÙĦ
    0.07
    erot
    0.07
    orns
    0.07
     irresist
    0.07
    Activations Density 0.022%

    No Known Activations