© 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. 27047
    Prev
    Next
    INDEX
    Explanations

    phrases related to ticket sales and online booking

    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
    -0.06
    ist
    -0.06
    ↵
    -0.06
     :
    -0.06
    ,
    -0.06
     (
    -0.05
    591
    -0.05
    ernals
    -0.05
     others
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    enga
    0.09
     oppon
    0.08
    елиÑĩ
    0.08
    ừng
    0.08
    íĬ¼
    0.08
    EPROM
    0.08
     EXEMPLARY
    0.08
    ÙĬÙĨات
    0.08
    azes
    0.08
    ÑĤаж
    0.08
    Activations Density 0.013%

    No Known Activations