© 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. 9-LLAMASCOPE-RES-131K
    11. 96284
    Prev
    Next
    INDEX
    Explanations

    phrases related to transitions between life and death

    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
    NTAX
    -0.07
    izard
    -0.07
    ritz
    -0.06
    ona
    -0.06
    hex
    -0.06
    íĸ
    -0.06
    onna
    -0.06
    หม
    -0.06
    ption
    -0.06
    serrat
    -0.06
    POSITIVE LOGITS
    frauen
    0.07
     Bros
    0.07
    agus
    0.07
    oÄŁ
    0.06
    iswa
    0.06
     Gat
    0.06
     “âĢ¦
    0.06
     å¹³
    0.06
     helpers
    0.06
    ustr
    0.06
    Activations Density 0.041%

    No Known Activations