© 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. 26338
    Prev
    Next
    INDEX
    Explanations

    specific dates and references to time

    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
    /***/
    -0.07
     Erot
    -0.07
     Late
    -0.06
    .GetUser
    -0.06
    ÙħاÙĨÛĮ
    -0.06
    ouser
    -0.06
    .metro
    -0.06
    μον
    -0.06
     Guerr
    -0.06
     Spl
    -0.05
    POSITIVE LOGITS
    lund
    0.07
    iyas
    0.07
    etten
    0.06
    anken
    0.06
    osph
    0.06
    geist
    0.06
    lue
    0.06
    iola
    0.06
    getInstance
    0.06
    acas
    0.06
    Activations Density 0.018%

    No Known Activations