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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72602
    Prev
    Next
    INDEX
    Explanations

    references to mining, particularly in the context of gold and copper industries

    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
    á»ijt
    -0.09
    ÄIJT
    -0.08
    inherits
    -0.07
    رÛĮاÙĨ
    -0.07
    AGMA
    -0.07
    irim
    -0.07
    Ïĥμ
    -0.07
    PIO
    -0.07
    raig
    -0.07
    isContained
    -0.07
    POSITIVE LOGITS
    eland
    0.06
    m
    0.05
    M
    0.05
    Thirty
    0.05
     .
    0.05
     Dy
    0.05
    IJ
    0.05
    etti
    0.05
    cool
    0.05
    arth
    0.05
    Activations Density 0.006%

    No Known Activations