© 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. 96464
    Prev
    Next
    INDEX
    Explanations

    references to the deceased or death-related terms

    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
    inals
    -0.06
    fort
    -0.06
    ise
    -0.06
    ford
    -0.06
    apa
    -0.06
    aggio
    -0.06
    88
    -0.06
    =Value
    -0.06
    سÙĪÙĨ
    -0.06
    fin
    -0.06
    POSITIVE LOGITS
    edl
    0.07
    IPH
    0.07
     Jennings
    0.07
    oÄŁlu
    0.06
    efs
    0.06
    Ïĩι
    0.06
     ones
    0.06
    rana
    0.06
     Hammond
    0.06
    acha
    0.06
    Activations Density 0.005%

    No Known Activations