© 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. 17-LLAMASCOPE-RES-131K
    11. 129147
    Prev
    Next
    INDEX
    Explanations

    elements of detailed storytelling and character development in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text discussing descriptive writing techniques, particularly how authors incorporate specific details about characters, settings, and scenes into their narratives.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    assi
    -0.06
     Title
    -0.06
    opot
    -0.06
     fac
    -0.05
    buah
    -0.05
    zan
    -0.05
     Corn
    -0.05
    argar
    -0.05
     demand
    -0.05
     produ
    -0.05
    POSITIVE LOGITS
     description
    0.16
     descriptions
    0.16
     describing
    0.15
     describe
    0.14
    description
    0.13
     Description
    0.12
    æııè¿°
    0.12
     describes
    0.12
    Descriptions
    0.12
     опиÑģ
    0.12
    Activations Density 0.068%

    No Known Activations