© 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. 15-LLAMASCOPE-RES-131K
    11. 89495
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishments or institutions and their status

    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
     ÐĴики
    -0.07
    ————————————————
    -0.06
    rum
    -0.06
     íĦ
    -0.06
    838
    -0.06
     rum
    -0.06
    èī
    -0.06
    ÅĦ
    -0.06
    rál
    -0.06
    -0.06
    POSITIVE LOGITS
    mue
    0.07
    ppe
    0.06
    mage
    0.06
    ritt
    0.06
    assen
    0.06
     Shea
    0.06
    licted
    0.06
    rary
    0.06
     telefone
    0.06
    ently
    0.06
    Activations Density 0.001%

    No Known Activations