© 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. 96383
    Prev
    Next
    INDEX
    Explanations

    references to national security concepts and strategies

    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
    ãģĵãģĿ
    -0.08
    ollah
    -0.07
    æŃ
    -0.07
    soever
    -0.07
    TERN
    -0.07
    isma
    -0.07
    ternet
    -0.07
    usra
    -0.07
    Disappear
    -0.07
    ÇIJ
    -0.07
    POSITIVE LOGITS
    ence
    0.06
     hed
    0.06
     Replica
    0.06
    ped
    0.06
    airs
    0.06
     Decomp
    0.06
    ED
    0.06
    DAC
    0.06
     fixing
    0.06
     Hed
    0.06
    Activations Density 0.003%

    No Known Activations