© 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. 57892
    Prev
    Next
    INDEX
    Explanations

    mentions of Facebook's features and challenges related to mobile and cloud gaming

    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
    inkel
    -0.07
    ascus
    -0.07
    aga
    -0.07
     Consultants
    -0.07
    abant
    -0.07
    apore
    -0.06
    ucken
    -0.06
    enso
    -0.06
    elm
    -0.06
    rollo
    -0.06
    POSITIVE LOGITS
     interest
    0.07
     entering
    0.07
     entered
    0.07
     capabilities
    0.06
    843
    0.06
    enter
    0.06
     compet
    0.06
     دخ
    0.06
     late
    0.06
    ekli
    0.06
    Activations Density 0.023%

    No Known Activations