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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87722
    Prev
    Next
    INDEX
    Explanations

    phrases related to making reservations and event planning

    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
     Damon
    -0.08
    asil
    -0.06
    unker
    -0.06
     Crest
    -0.06
    ves
    -0.06
    ABEL
    -0.06
    ahir
    -0.06
    679
    -0.06
    allery
    -0.06
    sbin
    -0.06
    POSITIVE LOGITS
     Reservation
    0.10
     reservation
    0.10
     booking
    0.09
     reservations
    0.09
     advance
    0.09
     reserva
    0.09
     Reserve
    0.08
    advance
    0.08
     reserv
    0.08
    reservation
    0.08
    Activations Density 0.166%

    No Known Activations