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. 5036
    Prev
    Next
    INDEX
    Explanations

    quantities and types of ground meat in recipes

    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
    ipp
    -0.08
    ippo
    -0.07
    NP
    -0.06
    acs
    -0.06
    ncy
    -0.06
     Sorted
    -0.06
    à¸į
    -0.06
     giải
    -0.06
    olib
    -0.06
    BYTES
    -0.06
    POSITIVE LOGITS
    AGMA
    0.07
    auer
    0.06
    eder
    0.06
    erosis
    0.06
    apiro
    0.06
    572
    0.06
     Backup
    0.06
    kle
    0.06
    agnostics
    0.06
    shake
    0.06
    Activations Density 0.025%

    No Known Activations