© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40591
    Prev
    Next
    INDEX
    Explanations

    mentions of water-related projects and initiatives by the PepsiCo Foundation

    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
     sper
    -0.08
    hrad
    -0.07
     Antar
    -0.07
     Å¡tÄĽ
    -0.07
    веÑī
    -0.07
    gün
    -0.07
    :UITableView
    -0.07
    ordo
    -0.07
     Kore
    -0.07
     bred
    -0.07
    POSITIVE LOGITS
     global
    0.10
     Global
    0.08
     GLOBAL
    0.08
    global
    0.07
     globally
    0.07
     consumer
    0.07
     Nest
    0.07
    Global
    0.07
     worldwide
    0.06
    GLOBAL
    0.06
    Activations Density 0.023%

    No Known Activations