© 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. 88325
    Prev
    Next
    INDEX
    Explanations

    phrases related to storytelling and personal narratives in the context of films

    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
    ɵ
    -0.08
    ipt
    -0.08
    esan
    -0.07
    lemen
    -0.07
    IFA
    -0.07
    ptal
    -0.07
     neod
    -0.07
    Submitting
    -0.07
     Xt
    -0.07
     æ©
    -0.07
    POSITIVE LOGITS
     Chicago
    0.10
     Barack
    0.08
    Chicago
    0.07
     chicago
    0.07
     Illinois
    0.07
     Obama
    0.06
     Wass
    0.06
     Mandela
    0.06
     African
    0.06
     programmes
    0.06
    Activations Density 0.006%

    No Known Activations