© 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. 40181
    Prev
    Next
    INDEX
    Explanations

    mentions of messaging applications, particularly WhatsApp

    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
    usb
    -0.07
     Synd
    -0.07
    theless
    -0.07
    hunter
    -0.06
    hall
    -0.06
     Ulus
    -0.06
    UMB
    -0.06
    shape
    -0.06
    kits
    -0.06
    ocard
    -0.06
    POSITIVE LOGITS
    s
    0.07
    inesis
    0.07
    frica
    0.07
    ois
    0.07
    eldon
    0.07
    infer
    0.06
    rooms
    0.06
     latter
    0.06
    aroo
    0.06
    ustomed
    0.06
    Activations Density 0.002%

    No Known Activations