© 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. 127832
    Prev
    Next
    INDEX
    Explanations

    references to key political figures and their roles in diplomatic relations

    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
    amera
    -0.07
    inx
    -0.07
    izers
    -0.06
    ulaire
    -0.06
    ocker
    -0.06
    801
    -0.06
    estic
    -0.06
    735
    -0.06
    009
    -0.06
    enses
    -0.06
    POSITIVE LOGITS
     deleg
    0.07
    ivent
    0.07
    uÄį
    0.07
    iaux
    0.06
    ulace
    0.06
    inea
    0.06
     Yug
    0.06
     Kr
    0.06
    eti
    0.06
    ä¾
    0.06
    Activations Density 0.017%

    No Known Activations