© 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. 15-LLAMASCOPE-RES-131K
    11. 27477
    Prev
    Next
    INDEX
    Explanations

    phrases related to research, experimentation, and laboratory settings

    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
     Keller
    -0.06
     territory
    -0.06
    ,
    -0.06
     flesh
    -0.06
    ervas
    -0.05
    .Cloud
    -0.05
     Shall
    -0.05
     familia
    -0.05
     territor
    -0.05
     Automatic
    -0.05
    POSITIVE LOGITS
     laboratory
    0.11
    isol
    0.09
     artificially
    0.09
    .synthetic
    0.09
     theoret
    0.09
     abstract
    0.09
     isolated
    0.09
     lab
    0.09
     abstraction
    0.09
     artificial
    0.08
    Activations Density 0.110%

    No Known Activations