© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71676
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate yielding to or succumbing to various pressures and temptations

    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
    iator
    -0.07
    άβ
    -0.07
    ignet
    -0.07
     Reed
    -0.07
    rame
    -0.07
     Jeb
    -0.07
    OrElse
    -0.07
    tep
    -0.07
    anie
    -0.07
     Jewel
    -0.07
    POSITIVE LOGITS
     temptation
    0.11
     pressure
    0.10
     pressures
    0.09
     demands
    0.09
     Pressure
    0.07
     demand
    0.07
     requests
    0.07
     fate
    0.07
     tempt
    0.07
    975
    0.07
    Activations Density 0.008%

    No Known Activations