© 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. 2772
    Prev
    Next
    INDEX
    Explanations

    references and discussions about processes involved in societal and organizational governance

    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
    esan
    -0.07
     dealloc
    -0.06
     Fairy
    -0.06
     rewarding
    -0.06
     dabei
    -0.06
     Barker
    -0.06
    arma
    -0.06
    ray
    -0.05
    jay
    -0.05
    arga
    -0.05
    POSITIVE LOGITS
     later
    0.12
    later
    0.11
     später
    0.11
    Later
    0.09
     Later
    0.09
     subsequently
    0.09
    åIJİ
    0.08
     latter
    0.08
     echoed
    0.08
     pozdÄĽji
    0.08
    Activations Density 0.106%

    No Known Activations