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. 43966
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in technical or mathematical texts

    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
    ancode
    -0.07
    isz
    -0.06
     chiff
    -0.06
     Vinci
    -0.06
     carr
    -0.06
    jong
    -0.06
     uchar
    -0.05
     Tillerson
    -0.05
    etur
    -0.05
     escort
    -0.05
    POSITIVE LOGITS
     brewery
    0.26
     beer
    0.24
     breweries
    0.24
     Brewery
    0.23
     brewers
    0.23
     beers
    0.23
     brew
    0.22
    Beer
    0.22
    beer
    0.22
     brewing
    0.21
    Activations Density 0.003%

    No Known Activations