© 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. 26465
    Prev
    Next
    INDEX
    Explanations

    references to scientific agencies and panels related to health and environmental safety

    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
     facilities
    -0.06
    fik
    -0.06
     Kami
    -0.06
    éijij
    -0.06
    akit
    -0.06
     Asi
    -0.05
    /add
    -0.05
    iele
    -0.05
    ehen
    -0.05
     sworn
    -0.05
    POSITIVE LOGITS
    psc
    0.07
    ures
    0.07
    Invoker
    0.07
    lest
    0.07
    uring
    0.07
    orary
    0.07
    pci
    0.07
    yal
    0.07
    erna
    0.07
    cano
    0.07
    Activations Density 0.003%

    No Known Activations