© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to physical systems, particularly in engineering or scientific 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
    ansi
    -0.07
     sur
    -0.06
     of
    -0.06
     mol
    -0.06
    583
    -0.06
    .nan
    -0.06
     deb
    -0.05
     set
    -0.05
    lotte
    -0.05
    fully
    -0.05
    POSITIVE LOGITS
     size
    0.11
    size
    0.10
    _size
    0.08
    Size
    0.08
     ún
    0.07
     Size
    0.07
    ois
    0.07
     içi
    0.07
     sizes
    0.07
    елик
    0.07
    Activations Density 0.095%

    No Known Activations