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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5053
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict, struggle, and emotional experiences

    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
     segreg
    -0.08
     erect
    -0.08
     dispatch
    -0.08
     chuck
    -0.08
    inject
    -0.07
     applaud
    -0.07
     cripp
    -0.07
     abort
    -0.07
     trunc
    -0.07
     wash
    -0.07
    POSITIVE LOGITS
     harvested
    0.08
     shared
    0.07
     distributed
    0.07
     repaired
    0.07
     leased
    0.07
     cru
    0.07
     rented
    0.06
     nurs
    0.06
     protected
    0.06
     lived
    0.06
    Activations Density 0.427%

    No Known Activations