© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88517
    Prev
    Next
    INDEX
    Explanations

    phrases related to querying databases and data extraction

    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
     Dum
    -0.07
    late
    -0.06
     ìŀħëĭĪëĭ¤
    -0.06
     pret
    -0.06
    ynet
    -0.06
    rades
    -0.06
    .unbind
    -0.05
     Bail
    -0.05
    atted
    -0.05
    repr
    -0.05
    POSITIVE LOGITS
    ï¼Ł↵
    0.07
    edla
    0.07
     forIndexPath
    0.07
    agini
    0.06
    åĬŁ
    0.06
    )?↵
    0.06
    createCommand
    0.06
    eggies
    0.06
    LARI
    0.06
    .styleable
    0.06
    Activations Density 0.027%

    No Known Activations