© 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. 9-LLAMASCOPE-RES-131K
    11. 96389
    Prev
    Next
    INDEX
    Explanations

    terms associated with organizations, legal institutions, and their significance in various contexts

    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
    inal
    -0.07
    ãģĹãģı
    -0.07
    ensa
    -0.06
    abad
    -0.06
    izable
    -0.06
    inals
    -0.06
    tgl
    -0.06
    mens
    -0.06
    tsy
    -0.06
    ienen
    -0.06
    POSITIVE LOGITS
    openh
    0.07
    illery
    0.07
    ibox
    0.07
    getter
    0.06
    'gc
    0.06
    ÅĻi
    0.06
    /***/
    0.06
    ooks
    0.06
     ru
    0.06
     Hin
    0.06
    Activations Density 0.105%

    No Known Activations