© 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. 89345
    Prev
    Next
    INDEX
    Explanations

    terms and names related to cultural or historical significance

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

    Text segments that provide etymological information or translations of names, terms, or titles, often using phrases like "name is," "translated," "meaning," or "literally."

    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
    εί
    -0.07
    नल
    -0.07
    erras
    -0.07
    //{{
    -0.07
     RuntimeObject
    -0.07
    .VERSION
    -0.07
    _residual
    -0.07
    кид
    -0.06
    .FontStyle
    -0.06
    coder
    -0.06
    POSITIVE LOGITS
     literally
    0.12
     means
    0.10
     meaning
    0.10
    liter
    0.09
     Means
    0.09
     lit
    0.09
    meaning
    0.08
    means
    0.08
    lit
    0.08
     literal
    0.08
    Activations Density 0.101%

    No Known Activations