© 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. 61872
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling and character development

    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
     Clarkson
    -0.07
    urr
    -0.06
    ä¸ĸç´Ģ
    -0.06
     shop
    -0.06
    à¥įण
    -0.06
    rases
    -0.06
     Hayward
    -0.06
    Ÿ
    -0.05
    ëĬIJ
    -0.05
    rey
    -0.05
    POSITIVE LOGITS
     novel
    0.10
     author
    0.10
     Author
    0.09
     novels
    0.09
     authors
    0.09
     Authors
    0.09
    authors
    0.09
     Writing
    0.09
    @author
    0.08
    author
    0.08
    Activations Density 0.419%

    No Known Activations