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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 17095
    Prev
    Next
    INDEX
    Explanations

    numerical data related to travel and transportation logistics

    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
    ваÑĢ
    -0.07
    Truthy
    -0.06
    ॰
    -0.06
    áy
    -0.06
    ederal
    -0.06
     имÑĥ
    -0.06
     BaÅŁkan
    -0.06
     loose
    -0.06
    PÅĻÃŃ
    -0.06
     {{{
    -0.06
    POSITIVE LOGITS
    HEST
    0.08
    -fontawesome
    0.07
     noreferrer
    0.07
    formace
    0.07
    timeofday
    0.07
     moden
    0.07
    ยาว
    0.06
    583
    0.06
     GenerationType
    0.06
    ote
    0.06
    Activations Density 0.006%

    No Known Activations