© 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. 76038
    Prev
    Next
    INDEX
    Explanations

    legislative terms related to regulations and mandates

    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
    abad
    -0.07
    auc
    -0.07
    çek
    -0.07
     Nah
    -0.07
     Canter
    -0.07
    usp
    -0.07
    uhn
    -0.07
     runApp
    -0.07
     Dash
    -0.06
    fbe
    -0.06
    POSITIVE LOGITS
    aroo
    0.07
    apult
    0.07
    .gs
    0.07
    0.07
     Portions
    0.06
    igator
    0.06
    byname
    0.06
    ellido
    0.06
    allon
    0.06
    abeth
    0.06
    Activations Density 0.026%

    No Known Activations