© 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. 15-LLAMASCOPE-RES-131K
    11. 62344
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and appreciation for experiences or activities

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

    Text segments where users express personal preferences, emotional connections, or alignment with something, often using first-person statements or predictions about what someone will enjoy or experience.

    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
    arez
    -0.07
    acas
    -0.06
    ARRANT
    -0.06
    iman
    -0.06
    wis
    -0.06
    èĢ
    -0.06
    allest
    -0.06
    ubat
    -0.06
    arsers
    -0.06
    æī¿
    -0.06
    POSITIVE LOGITS
     heaven
    0.08
    PPER
    0.07
    iture
    0.07
     dro
    0.07
     PERF
    0.06
     perfect
    0.06
     tslint
    0.06
    ầy
    0.06
    -types
    0.06
     Heaven
    0.06
    Activations Density 0.112%

    No Known Activations