© 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. 27419
    Prev
    Next
    INDEX
    Explanations

    references to centralized systems or organizations

    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
    ãĥĨãĥ«
    -0.07
    aturated
    -0.07
    ouv
    -0.07
    edom
    -0.07
    éļľ
    -0.07
    HEL
    -0.07
    erge
    -0.07
    æł·çļĦ
    -0.07
    _CSR
    -0.07
    ecs
    -0.07
    POSITIVE LOGITS
    most
    0.15
    ised
    0.11
    ities
    0.11
    ized
    0.11
    ization
    0.10
    izing
    0.10
    -most
    0.10
    isation
    0.09
    mente
    0.09
    izers
    0.09
    Activations Density 0.012%

    No Known Activations