© 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. 117997
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavioral advice and self-reflection

    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
    åģ·
    -0.06
    _boot
    -0.06
     dispro
    -0.06
     RSS
    -0.06
     Woo
    -0.05
    impan
    -0.05
    -boot
    -0.05
     reversed
    -0.05
    boot
    -0.05
     Rebecca
    -0.05
    POSITIVE LOGITS
    Specifier
    0.08
    asm
    0.07
    ogn
    0.07
    eshire
    0.07
     trending
    0.07
    obic
    0.07
    ùi
    0.07
     demand
    0.07
    Demand
    0.07
    iseum
    0.07
    Activations Density 0.000%

    No Known Activations