© 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. 83456
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal unrest and survival preparedness

    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
    ADI
    -0.08
    roys
    -0.08
    aland
    -0.07
    ÅĦst
    -0.07
    scal
    -0.07
    herited
    -0.07
    lük
    -0.07
     rencont
    -0.07
     ë§Į족
    -0.07
    makt
    -0.07
    POSITIVE LOGITS
     preparation
    0.09
     prepared
    0.09
     preparing
    0.08
     defensive
    0.08
     prepare
    0.08
     Prepared
    0.08
     Preparation
    0.08
     prepares
    0.07
     preparations
    0.07
     bunker
    0.07
    Activations Density 0.059%

    No Known Activations