© 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. 129556
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to subjects and actions

    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
    brig
    -0.07
     пÑĢид
    -0.06
    tran
    -0.06
    ÑĤÑİ
    -0.06
     trá»Ŀi
    -0.06
    ieber
    -0.06
    ÑĦа
    -0.06
    ifar
    -0.06
    ubi
    -0.06
    osa
    -0.06
    POSITIVE LOGITS
     EXEMPLARY
    0.08
     available
    0.07
     able
    0.07
    Tween
    0.07
    arton
    0.06
    -available
    0.06
     καÏĦα
    0.06
    asil
    0.06
    åĮĸ
    0.06
    arten
    0.06
    Activations Density 0.031%

    No Known Activations