© 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. 89285
    Prev
    Next
    INDEX
    Explanations

    elements related to authentication and security in programming 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
    (PHP
    -0.08
    اش
    -0.08
     åĦ
    -0.08
    (SP
    -0.08
    (æĹ¥
    -0.08
     DÄĽ
    -0.07
    THR
    -0.07
    ÛĮØ´
    -0.07
    ivec
    -0.07
    utar
    -0.07
    POSITIVE LOGITS
    âĢ¦↵
    0.06
    -labelledby
    0.06
    <|end_of_text|>
    0.06
    ...↵
    0.06
    acher
    0.06
     Pierce
    0.05
     character
    0.05
    bing
    0.05
     vast
    0.05
    bane
    0.05
    Activations Density 0.012%

    No Known Activations