© 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. 5-LLAMASCOPE-RES-131K
    11. 125700
    Prev
    Next
    INDEX
    Explanations

    references to rites of passage and age-related experiences

    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
    edia
    -0.08
    ickers
    -0.07
    edException
    -0.07
    à¥ĩम
    -0.06
    icker
    -0.06
    inder
    -0.06
    ards
    -0.06
    ail
    -0.06
    ieri
    -0.06
    ERC
    -0.06
    POSITIVE LOGITS
    glich
    0.06
    -prof
    0.06
    ocz
    0.06
    ÎłÏģο
    0.06
     kein
    0.06
     dag
    0.06
     Dove
    0.06
    ìŀĦ
    0.06
    ansi
    0.06
     orient
    0.06
    Activations Density 0.001%

    No Known Activations