© 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. 260
    Prev
    Next
    INDEX
    Explanations

    phrases related to mortality or the passing of individuals

    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
    esini
    -0.08
    ango
    -0.07
    iets
    -0.07
    etu
    -0.07
    cente
    -0.06
    rone
    -0.06
    iyah
    -0.06
    ène
    -0.06
    BOSE
    -0.06
    reb
    -0.06
    POSITIVE LOGITS
    رÙĬÙģ
    0.07
    ãģĭãģij
    0.06
    nez
    0.06
    eer
    0.06
     ConnectionState
    0.06
    _CTL
    0.06
    webkit
    0.06
     nationality
    0.06
    [assembly
    0.06
    gan
    0.06
    Activations Density 0.039%

    No Known Activations