© 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. 17-LLAMASCOPE-RES-131K
    11. 59790
    Prev
    Next
    INDEX
    Explanations

    references to the word "Rembrandt."

    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
    iously
    -0.07
    elen
    -0.07
    ergy
    -0.06
    heim
    -0.06
     neat
    -0.06
    ниÑĩ
    -0.06
    uzzle
    -0.06
    rompt
    -0.06
    richt
    -0.06
    ÐĿаÑģ
    -0.06
    POSITIVE LOGITS
    /rem
    0.09
    linger
    0.09
    rive
    0.08
    nants
    0.08
     Rem
    0.07
    iem
    0.07
    usat
    0.07
     rem
    0.07
    embrance
    0.07
    θÏħ
    0.07
    Activations Density 0.012%

    No Known Activations