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. 5050
    Prev
    Next
    INDEX
    Explanations

    comparative pricing information related to hotels

    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
    icot
    -0.07
    annis
    -0.07
    cona
    -0.07
    eye
    -0.06
    _DYNAMIC
    -0.06
    allest
    -0.06
    arton
    -0.06
    uit
    -0.06
     bit
    -0.06
    ãĥĥãĥĦ
    -0.06
    POSITIVE LOGITS
    ghi
    0.06
     Yad
    0.06
     Bookmark
    0.06
     White
    0.06
    ycastle
    0.06
     Rocky
    0.06
    вал
    0.06
     Berm
    0.06
     Wag
    0.06
     Bolton
    0.06
    Activations Density 0.000%

    No Known Activations