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. 5001
    Prev
    Next
    INDEX
    Explanations

    hotel amenities and features focused on comfort and luxury

    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
    ÑĤÑĢо
    -0.07
    ucus
    -0.07
    è¡Ŀ
    -0.07
    OMATIC
    -0.07
    owitz
    -0.06
    icter
    -0.06
    enburg
    -0.06
     Incorporated
    -0.06
    adesh
    -0.06
    stial
    -0.06
    POSITIVE LOGITS
     underst
    0.07
    irie
    0.07
    5
    0.06
    618
    0.06
     scr
    0.06
     Dahl
    0.06
    ارس
    0.06
    auen
    0.06
    _MT
    0.06
     refinement
    0.06
    Activations Density 0.023%

    No Known Activations