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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44006
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to accessibility and online services

    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
    reek
    -0.06
    vie
    -0.06
    bi
    -0.06
    arda
    -0.05
    esz
    -0.05
     Company
    -0.05
    company
    -0.05
     Intent
    -0.05
    arn
    -0.05
    INDOW
    -0.05
    POSITIVE LOGITS
     lawy
    0.12
     digit
    0.10
     courts
    0.10
     digitally
    0.10
     lawyer
    0.10
     digital
    0.10
     lawyers
    0.10
     litigation
    0.10
     juris
    0.09
     online
    0.09
    Activations Density 0.004%

    No Known Activations