© 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. 55525
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Wake" and related phrases

    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
    inha
    -0.08
    ekt
    -0.08
    æĥħ
    -0.07
    ίνα
    -0.07
    RLF
    -0.07
    rei
    -0.07
    edelta
    -0.07
    inho
    -0.07
    ADS
    -0.07
    orno
    -0.07
    POSITIVE LOGITS
    ley
    0.07
    field
    0.07
    isha
    0.07
    yr
    0.07
    fulness
    0.06
    ilee
    0.06
    -up
    0.06
    leys
    0.06
    atch
    0.06
    onom
    0.06
    Activations Density 0.005%

    No Known Activations