© 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. 29891
    Prev
    Next
    INDEX
    Explanations

    references to geographical boundaries or borders

    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
    olik
    -0.06
    оÑĢа
    -0.06
    INET
    -0.06
    обÑĢаз
    -0.06
    ARA
    -0.06
    رخ
    -0.06
    eko
    -0.06
    createForm
    -0.06
     Folding
    -0.06
    iÄį
    -0.05
    POSITIVE LOGITS
    rophe
    0.07
    éĤĬ
    0.07
     boundary
    0.07
    à¥įपर
    0.06
     border
    0.06
    fault
    0.06
    boundary
    0.06
    EMPL
    0.06
    zone
    0.06
     conven
    0.06
    Activations Density 0.009%

    No Known Activations