© 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. 75782
    Prev
    Next
    INDEX
    Explanations

    structured data or code elements, particularly focusing on syntax and formatting

    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
    olare
    -0.06
    aha
    -0.06
    :↵
    -0.06
     Protective
    -0.05
    etsy
    -0.05
    levator
    -0.05
    erp
    -0.05
     Warren
    -0.05
     Verg
    -0.05
     scans
    -0.05
    POSITIVE LOGITS
    GuidId
    0.07
    HeaderCode
    0.07
    OrDefault
    0.07
     Boyle
    0.07
    åħ¥ãĤĬ
    0.07
    oro
    0.07
    SSIP
    0.07
    BOSE
    0.07
    \OptionsResolver
    0.07
    adge
    0.06
    Activations Density 0.006%

    No Known Activations