© 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. 89171
    Prev
    Next
    INDEX
    Explanations

    references to quantities and statistical information

    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
     Jar
    -0.07
    jan
    -0.07
    onomic
    -0.07
    thon
    -0.06
     поÑĢ
    -0.06
     Salman
    -0.06
    leen
    -0.06
    itet
    -0.06
    udit
    -0.06
    entials
    -0.06
    POSITIVE LOGITS
    ationToken
    0.07
    ledo
    0.06
    .foundation
    0.06
    Loader
    0.06
    ONSE
    0.06
    егоÑĢ
    0.06
    _construct
    0.06
     agg
    0.06
    λοÏħ
    0.06
    .EventHandler
    0.06
    Activations Density 0.002%

    No Known Activations