© 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. 41102
    Prev
    Next
    INDEX
    Explanations

    references to architectural and cultural elements

    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
    Anywhere
    -0.07
    olk
    -0.07
    mie
    -0.07
    åħ³äºİ
    -0.07
    æ³½
    -0.07
    .community
    -0.07
     пÑĢип
    -0.06
     Swinger
    -0.06
    ÏħÏĢ
    -0.06
    ÑĢÑĸÑĪ
    -0.06
    POSITIVE LOGITS
     series
    0.07
    ãĤ·ãĥªãĥ¼ãĤº
    0.06
    ppers
    0.06
    itbart
    0.06
     clickable
    0.06
    cus
    0.06
    oubles
    0.06
     Index
    0.06
    oser
    0.05
    ija
    0.05
    Activations Density 0.042%

    No Known Activations