© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 78399
    Prev
    Next
    INDEX
    Explanations

    references to specific events, organizations, and their operations over time

    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
    öst
    -0.06
     Biological
    -0.06
     ways
    -0.06
    Marks
    -0.06
    ç
    -0.06
    bes
    -0.06
     åIJī
    -0.06
    оÑģÑĤав
    -0.06
    essel
    -0.06
     TextStyle
    -0.06
    POSITIVE LOGITS
     headquarters
    0.09
    location
    0.09
    Location
    0.08
     location
    0.07
    locate
    0.07
     Location
    0.07
    ÙĤع
    0.07
    LOCATION
    0.07
     HQ
    0.07
     majority
    0.07
    Activations Density 0.052%

    No Known Activations