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. 43894
    Prev
    Next
    INDEX
    Explanations

    references to diversity and representation in the film industry

    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
     filme
    -0.08
    Movies
    -0.08
    film
    -0.08
     movies
    -0.08
     Movies
    -0.08
     filmes
    -0.08
     films
    -0.08
     cinema
    -0.08
    OKIE
    -0.07
     cinematic
    -0.07
    POSITIVE LOGITS
     creator
    0.13
     executive
    0.13
     exec
    0.13
     executives
    0.12
     creators
    0.12
     producers
    0.11
     production
    0.11
     network
    0.11
     networks
    0.11
     show
    0.11
    Activations Density 0.035%

    No Known Activations