© 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. 55338
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling and creative expression

    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
    iants
    -0.07
    keiten
    -0.07
    .subtitle
    -0.07
     عÙĦÙĬÙĩ
    -0.07
    ̧
    -0.07
    cant
    -0.07
    .Parser
    -0.07
     UClass
    -0.07
    arp
    -0.07
    еÑģ
    -0.07
    POSITIVE LOGITS
     reign
    0.07
     can
    0.07
    uk
    0.07
     reg
    0.07
     are
    0.06
     could
    0.06
     suddenly
    0.06
     Reign
    0.06
     literally
    0.06
     is
    0.06
    Activations Density 0.096%

    No Known Activations