© 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. 17291
    Prev
    Next
    INDEX
    Explanations

    specific components and instructions related to wine-making kits

    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
    ,
    -0.07
    åĿĤ
    -0.06
    athi
    -0.06
    Calibri
    -0.05
    -
    -0.05
     Gel
    -0.05
    borg
    -0.05
     dod
    -0.05
    regon
    -0.05
     can
    -0.05
    POSITIVE LOGITS
     kit
    0.11
    -kit
    0.10
    -components
    0.10
    kit
    0.09
     components
    0.09
     Kit
    0.09
     parts
    0.09
    .getComponent
    0.09
    .components
    0.09
    -parts
    0.09
    Activations Density 0.023%

    No Known Activations