© 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. 16028
    Prev
    Next
    INDEX
    Explanations

    interactions that suggest hospitality or welcoming gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases expressing invitation, welcome, or permission for someone to enter a space or make themselves comfortable.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ucken
    -0.07
    erra
    -0.06
    err
    -0.06
    ì¶ľ
    -0.06
    irie
    -0.06
    utra
    -0.06
    flush
    -0.06
    elle
    -0.06
    wy
    -0.06
    emption
    -0.06
    POSITIVE LOGITS
     freely
    0.09
    237
    0.07
     Barker
    0.07
    grab
    0.07
    olume
    0.07
    ihil
    0.07
    ium
    0.07
    cycl
    0.07
     ìŀIJìľł
    0.07
    é³´
    0.06
    Activations Density 0.053%

    No Known Activations