© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75463
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or suggestions related to using or handling data and technology

    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
    Also
    -0.08
     also
    -0.08
     Also
    -0.08
     however
    -0.08
    also
    -0.07
     other
    -0.07
     others
    -0.07
     ÙĨÛĮز
    -0.07
     också
    -0.07
    ä¹Łæĺ¯
    -0.07
    POSITIVE LOGITS
     ÙħØ«ÙĦا
    0.09
    inear
    0.08
    coni
    0.08
    ilog
    0.07
     etwa
    0.07
     ÐĿапÑĢимеÑĢ
    0.07
    453
    0.07
     Whereas
    0.07
    ucch
    0.07
     whereas
    0.07
    Activations Density 0.090%

    No Known Activations