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. 5049
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and chemical properties

    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
    _tF
    -0.09
    _tA
    -0.08
    groupon
    -0.08
    _tD
    -0.08
    _tC
    -0.08
    idot
    -0.08
    ahas
    -0.08
    ongyang
    -0.08
    swers
    -0.08
    alion
    -0.08
    POSITIVE LOGITS
     ex
    0.06
     prostitu
    0.06
     \
    0.06
    ym
    0.06
     Ex
    0.06
     Price
    0.06
     Cop
    0.06
     Qu
    0.06
     prostit
    0.06
    ex
    0.05
    Activations Density 0.009%

    No Known Activations