© 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. 15-LLAMASCOPE-RES-131K
    11. 90559
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a "story" or narrative

    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
     Barrier
    -0.07
    HELL
    -0.07
    aras
    -0.07
    ifice
    -0.07
    InSeconds
    -0.06
    ÙĬج
    -0.06
    fon
    -0.06
    vig
    -0.06
     hell
    -0.06
     proje
    -0.06
    POSITIVE LOGITS
     story
    0.08
     stories
    0.07
    /history
    0.07
    нÑİ
    0.07
     behind
    0.07
    896
    0.07
    ddit
    0.06
    afort
    0.06
    agues
    0.06
    stories
    0.06
    Activations Density 0.014%

    No Known Activations