© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93969
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional engagement and storytelling in marketing and advertising

    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
    iec
    -0.07
    akh
    -0.07
    duc
    -0.07
     requestOptions
    -0.06
    /cms
    -0.06
    oÅĪ
    -0.06
    ãĢħ
    -0.06
     Junk
    -0.06
    lek
    -0.06
    Ending
    -0.06
    POSITIVE LOGITS
    oplayer
    0.08
     Brands
    0.08
    ãĤĵãģ©
    0.08
     artık
    0.07
    å¤ķ
    0.07
     brands
    0.07
     Era
    0.07
    -brand
    0.07
     crt
    0.07
    andır
    0.06
    Activations Density 0.008%

    No Known Activations