© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3824
    Prev
    Next
    INDEX
    Explanations

    phrases related to booking and reservations

    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
    òi
    -0.07
    lun
    -0.06
    eof
    -0.06
    xEF
    -0.06
    eft
    -0.06
    jen
    -0.06
    SEQ
    -0.06
    ica
    -0.06
    ovat
    -0.06
    imon
    -0.06
    POSITIVE LOGITS
    ctor
    0.07
     reservation
    0.07
     purchase
    0.07
     SpringApplication
    0.07
     initial
    0.06
    posite
    0.06
    yntax
    0.06
     ÙħÙĤد
    0.06
    ToDevice
    0.06
    oucher
    0.06
    Activations Density 0.022%

    No Known Activations