© 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. 15-LLAMASCOPE-RES-131K
    6. 90810
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and data types

    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
    Brains
    -0.07
    Difficulty
    -0.07
    declspec
    -0.07
    Ñģклад
    -0.07
    raya
    -0.07
    .Reader
    -0.07
    ãģ³
    -0.07
    clare
    -0.07
    .nasa
    -0.07
    iston
    -0.06
    POSITIVE LOGITS
     genetics
    0.06
    ilogy
    0.06
    CT
    0.05
     Atkins
    0.05
     smoke
    0.05
    allery
    0.05
    ëįķ
    0.05
    roc
    0.05
    ustria
    0.05
    imes
    0.05
    Activations Density 0.001%

    No Known Activations