© 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. 15-LLAMASCOPE-RES-131K
    11. 26922
    Prev
    Next
    INDEX
    Explanations

    themes surrounding personal struggles and moral complexities

    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
    rlen
    -0.06
    rico
    -0.06
     promin
    -0.06
    ÑģилÑĮ
    -0.06
     Чи
    -0.06
    ohl
    -0.06
    attery
    -0.06
    usaha
    -0.06
    coles
    -0.06
    åĹ
    -0.06
    POSITIVE LOGITS
     everyday
    0.14
     daily
    0.11
     routine
    0.10
     ordinary
    0.10
     quotid
    0.10
     Everyday
    0.10
    ignon
    0.10
    daily
    0.09
     quot
    0.09
     regular
    0.09
    Activations Density 0.032%

    No Known Activations