Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5234
    Prev
    Next
    INDEX
    Explanations

    elements related to theme customization in web development

    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
     buffs
    -0.07
    GenerationStrategy
    -0.07
     trh
    -0.07
    ãĥ¼ãĥĭ
    -0.07
    croft
    -0.07
    mitt
    -0.07
    ưỡng
    -0.07
    adh
    -0.07
     çİ
    -0.06
     赤
    -0.06
    POSITIVE LOGITS
     Woo
    0.07
    inne
    0.07
     Vega
    0.07
     retina
    0.06
     Jeg
    0.06
     par
    0.06
     social
    0.06
     included
    0.06
     Cherry
    0.06
     
    0.06
    Activations Density 0.011%

    No Known Activations