© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129910
    Prev
    Next
    INDEX
    Explanations

    phrases related to examples and usage cases 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
    ниÑĨÑĮ
    -0.06
    ff
    -0.06
     reserves
    -0.06
    ìm
    -0.06
    ault
    -0.05
     demek
    -0.05
     Pell
    -0.05
    xd
    -0.05
    iece
    -0.05
    argin
    -0.05
    POSITIVE LOGITS
     these
    0.13
    these
    0.12
    è¿Ļç§į
    0.11
     this
    0.11
    è¿Ļä¸Ģ
    0.10
     such
    0.10
    this
    0.10
     ìĿ´ë٬íķľ
    0.09
     nÃły
    0.09
    è¿ĻäºĽ
    0.09
    Activations Density 0.096%

    No Known Activations