© 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. 56671
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to user interface components in programming

    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
    éļĨ
    -0.07
    qml
    -0.07
    /GPL
    -0.07
    adro
    -0.07
    odb
    -0.07
    reib
    -0.06
    lide
    -0.06
    bole
    -0.06
    urum
    -0.06
    ScrollIndicator
    -0.06
    POSITIVE LOGITS
     Cass
    0.06
     Gus
    0.06
    deb
    0.06
     Morr
    0.06
    838
    0.06
    eme
    0.06
    ipa
    0.06
     borderTop
    0.06
    _inches
    0.06
    eb
    0.06
    Activations Density 0.026%

    No Known Activations