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. 5045
    Prev
    Next
    INDEX
    Explanations

    French words or phrases, particularly variations of "sous" and "sousa"

    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
     A
    -0.07
     in
    -0.06
     
    -0.06
     chief
    -0.06
     for
    -0.06
     on
    -0.06
    rais
    -0.06
     Chief
    -0.06
     g
    -0.06
     share
    -0.06
    POSITIVE LOGITS
    eref
    0.09
    	Copyright
    0.08
    WISE
    0.08
    okit
    0.07
     Erotik
    0.07
     sey
    0.07
    pies
    0.07
     Arbor
    0.07
    .writeln
    0.07
     ฿
    0.07
    Activations Density 0.000%

    No Known Activations