© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62338
    Prev
    Next
    INDEX
    Explanations

    references to the journey and challenges of artistic careers

    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
    á»ĭp
    -0.07
    arih
    -0.07
    agner
    -0.07
    anean
    -0.07
    eriod
    -0.07
    usto
    -0.07
    krv
    -0.07
    ç¹ģ
    -0.07
    ebo
    -0.07
    elsing
    -0.07
    POSITIVE LOGITS
     talent
    0.11
     Talent
    0.10
     audition
    0.09
     talents
    0.07
     modeling
    0.07
     Dreams
    0.07
     star
    0.07
     modelling
    0.07
     dream
    0.07
     dreams
    0.07
    Activations Density 0.311%

    No Known Activations