Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43922
    Prev
    Next
    INDEX
    Explanations

    elements of world-building in narratives

    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
    oga
    -0.06
    ennen
    -0.06
    illa
    -0.06
    é³
    -0.06
    Torrent
    -0.06
    wagon
    -0.06
    deo
    -0.06
     зал
    -0.06
     cade
    -0.06
    ráž
    -0.06
    POSITIVE LOGITS
     setting
    0.14
     lands
    0.12
     world
    0.12
     land
    0.12
    setting
    0.10
     Setting
    0.10
     settings
    0.10
     fantasy
    0.10
     environment
    0.10
     continent
    0.10
    Activations Density 0.047%

    No Known Activations