© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103781
    Prev
    Next
    INDEX
    Explanations

    phrases related to making reservations and managing bookings

    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
     hence
    -0.06
     terror
    -0.06
    stack
    -0.06
    elop
    -0.06
    holm
    -0.06
    rou
    -0.06
    essen
    -0.06
     dán
    -0.06
     ré
    -0.06
    avl
    -0.06
    POSITIVE LOGITS
    538
    0.07
    виÑħ
    0.07
    .appspot
    0.07
     Dam
    0.07
     pumps
    0.06
    <TSource
    0.06
    olle
    0.06
    ãĤ¿ãĥ«
    0.06
     Damage
    0.06
     Pump
    0.06
    Activations Density 0.008%

    No Known Activations