© 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. 28703
    Prev
    Next
    INDEX
    Explanations

    specific mathematical or statistical terminology and coding concepts

    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
    EXTERN
    -0.07
     serialVersionUID
    -0.07
     tamb
    -0.07
    ارج
    -0.07
    æ´ĭ
    -0.07
    nodoc
    -0.07
    istics
    -0.07
    лег
    -0.07
    atatype
    -0.07
    eÅŁit
    -0.07
    POSITIVE LOGITS
     whereas
    0.07
     并
    0.07
    并
    0.06
    anz
    0.06
    åıĬåħ¶
    0.06
    ëĵ¤ê³¼
    0.06
     ê·¸ë¦¬ê³ł
    0.06
    acci
    0.06
    intro
    0.06
    aleb
    0.06
    Activations Density 0.022%

    No Known Activations