© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 29533
    Prev
    Next
    INDEX
    Explanations

    technical terms related to encoding and encryption

    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
    kees
    -0.07
    ัà¸Ļà¸Ńà¸Ńà¸ģ
    -0.07
     Anatomy
    -0.07
    agh
    -0.07
    ois
    -0.07
    erk
    -0.07
    peri
    -0.07
    амп
    -0.07
    peria
    -0.07
    keh
    -0.07
    POSITIVE LOGITS
    :NSUTF
    0.07
    rou
    0.06
    hift
    0.06
    628
    0.06
    =UTF
    0.06
     bile
    0.06
     Basket
    0.05
     Babe
    0.05
     queryInterface
    0.05
     touch
    0.05
    Activations Density 0.002%

    No Known Activations