© 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. 15-LLAMASCOPE-RES-131K
    11. 578
    Prev
    Next
    INDEX
    Explanations

    references to political and bureaucratic structures

    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
    processable
    -0.06
    aml
    -0.06
    uben
    -0.06
    ulu
    -0.06
    amin
    -0.06
    anc
    -0.06
    odus
    -0.06
     dostat
    -0.06
    ÑĢаб
    -0.06
     hypoc
    -0.06
    POSITIVE LOGITS
     each
    0.09
     individual
    0.09
     separate
    0.08
    åIJĦ
    0.08
    ango
    0.07
    spl
    0.07
    fragment
    0.07
    individual
    0.07
     spl
    0.07
     åIJĦ
    0.07
    Activations Density 0.039%

    No Known Activations