© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 78489
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to death and the registration process associated with it

    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
    usa
    -0.06
    ény
    -0.06
    ango
    -0.06
    lea
    -0.06
    ANGO
    -0.06
     sak
    -0.06
     mailed
    -0.06
    éģĬ
    -0.05
    arella
    -0.05
     Innoc
    -0.05
    POSITIVE LOGITS
     Funeral
    0.07
     funeral
    0.07
     crem
    0.07
    æŃ»äº¡
    0.07
     pall
    0.07
    çļĦåľ°æĸ¹
    0.06
    odie
    0.06
     PHONE
    0.06
    708
    0.06
     telephone
    0.06
    Activations Density 0.004%

    No Known Activations