© 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. 17-LLAMASCOPE-RES-131K
    11. 105989
    Prev
    Next
    INDEX
    Explanations

    references to user interaction with a website, particularly related to visits and activity tracking

    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
    ког
    -0.07
    Ú©ÙĪ
    -0.06
     пÑĢавда
    -0.06
    acic
    -0.06
    анов
    -0.06
    ierten
    -0.06
    prehensive
    -0.06
    akes
    -0.05
     Peripheral
    -0.05
    aln
    -0.05
    POSITIVE LOGITS
     website
    0.09
    website
    0.08
    .website
    0.08
     websites
    0.08
    elper
    0.08
    ãĤµãĤ¤ãĥĪ
    0.07
     site
    0.07
     Website
    0.07
    ç½ijç«Ļ
    0.07
    ayi
    0.07
    Activations Density 0.001%

    No Known Activations