© 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. 105651
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental organizations and their functions

    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
     Hedge
    -0.06
    ÑĢой
    -0.06
    eries
    -0.06
     Becker
    -0.06
     Middleton
    -0.06
     superv
    -0.06
     Bry
    -0.06
     gall
    -0.05
     himself
    -0.05
     Pierce
    -0.05
    POSITIVE LOGITS
     itself
    0.09
    GLOBALS
    0.08
    umba
    0.08
    yms
    0.07
    iÃŁ
    0.07
     its
    0.07
    erness
    0.07
     FUNCTIONS
    0.07
    Animating
    0.07
    oba
    0.07
    Activations Density 0.073%

    No Known Activations