© 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. 9-LLAMASCOPE-RES-131K
    11. 95330
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to decoration and embellishment

    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
    dle
    -0.07
    loo
    -0.07
     Depths
    -0.07
    гл
    -0.07
    uggage
    -0.07
    OperationException
    -0.07
    itaire
    -0.07
    /do
    -0.07
    odore
    -0.07
    233
    -0.07
    POSITIVE LOGITS
    æŀĿ
    0.08
    lilik
    0.07
     CIM
    0.06
    amu
    0.06
     trim
    0.06
    .timing
    0.06
    žel
    0.06
    obia
    0.06
    ıyla
    0.06
    ulary
    0.06
    Activations Density 0.012%

    No Known Activations