© 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. 86763
    Prev
    Next
    INDEX
    Explanations

    references to traditional customs or practices

    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
    iw
    -0.08
    560
    -0.07
    бом
    -0.07
    hood
    -0.07
    ropy
    -0.07
    drive
    -0.07
    naire
    -0.07
    iyah
    -0.06
    osal
    -0.06
    ries
    -0.06
    POSITIVE LOGITS
    itionally
    0.14
    ITIONAL
    0.10
    itional
    0.09
    emark
    0.08
    بط
    0.07
    viso
    0.07
    itel
    0.07
    ç½
    0.07
    icional
    0.07
    luet
    0.07
    Activations Density 0.005%

    No Known Activations