© 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 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. 88143
    Prev
    Next
    INDEX
    Explanations

    details related to travel and itinerary 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
    onis
    -0.07
    áu
    -0.07
    uman
    -0.06
    ÑĪкÑĥ
    -0.06
    ảo
    -0.06
     typings
    -0.06
     Arap
    -0.06
    å±Ĩ
    -0.06
    ÑĪев
    -0.06
    edo
    -0.06
    POSITIVE LOGITS
    aira
    0.07
    ilen
    0.07
    ë´ī
    0.06
    opis
    0.06
    aea
    0.06
    :view
    0.06
     UNESCO
    0.06
    ãĥ¼ãĤ¸
    0.06
     porter
    0.06
     wherever
    0.06
    Activations Density 0.017%

    No Known Activations