© 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. 128215
    Prev
    Next
    INDEX
    Explanations

    references to various groups or details about subjects in a document

    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
    ellig
    -0.07
     typeid
    -0.07
    lid
    -0.07
    xad
    -0.07
    onde
    -0.07
    feit
    -0.06
    sville
    -0.06
    بط
    -0.06
    porter
    -0.06
    ptal
    -0.06
    POSITIVE LOGITS
     include
    0.09
     one
    0.07
     Include
    0.07
     Among
    0.07
     among
    0.07
     besides
    0.07
    ä¹ĭä¸Ģ
    0.07
    bes
    0.06
     apart
    0.06
     figure
    0.06
    Activations Density 0.011%

    No Known Activations