© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 97133
    Prev
    Next
    INDEX
    Explanations

    punctuations and code-related syntax elements

    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
    eyer
    -0.07
    :
    -0.06
    angkan
    -0.06
    OfWork
    -0.06
    wie
    -0.06
    ÑĦекÑĤив
    -0.06
    alement
    -0.05
    oba
    -0.05
    ben
    -0.05
    irth
    -0.05
    POSITIVE LOGITS
     ÑĤв
    0.07
    oman
    0.07
     Sink
    0.07
    خاÙĨ
    0.07
     tisk
    0.06
    дÑĸл
    0.06
     Kaynak
    0.06
    ÅĻev
    0.06
    -FIRST
    0.06
    .jdesktop
    0.06
    Activations Density 0.020%

    No Known Activations