© 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. 16888
    Prev
    Next
    INDEX
    Explanations

    elements related to humor and plot twists in storytelling

    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
     roli
    -0.06
    ixe
    -0.06
    ragen
    -0.06
    ucha
    -0.06
     finally
    -0.05
    -public
    -0.05
    uch
    -0.05
    /Search
    -0.05
     swept
    -0.05
    alfa
    -0.05
    POSITIVE LOGITS
     references
    0.07
     References
    0.07
    δά
    0.07
    references
    0.07
    Introduced
    0.07
    pedia
    0.07
    ึà¸ģ
    0.06
    dio
    0.06
    tram
    0.06
    ULE
    0.06
    Activations Density 0.028%

    No Known Activations