© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55615
    Prev
    Next
    INDEX
    Explanations

    references to indoor plants and their arrangement in home decor

    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
    odom
    -0.06
    çª
    -0.06
     exc
    -0.06
     excel
    -0.06
     conjug
    -0.05
    .openConnection
    -0.05
    ãĤ·ãĥ£
    -0.05
     vault
    -0.05
     Rog
    -0.05
    jah
    -0.05
    POSITIVE LOGITS
    /display
    0.07
     Clearance
    0.07
     addCriterion
    0.07
     Displays
    0.07
    fdb
    0.07
    obo
    0.07
    display
    0.07
    éī
    0.07
     Display
    0.07
    ernals
    0.07
    Activations Density 0.008%

    No Known Activations