© 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. 86798
    Prev
    Next
    INDEX
    Explanations

    buttons related to actions in a user interface, specifically those that are commonly used for tasks like uploading, canceling, or removing items

    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
    lector
    -0.07
    Ú¯ÙĦ
    -0.07
    ynes
    -0.07
    uC
    -0.07
    thro
    -0.07
    rade
    -0.07
    onio
    -0.07
    ycin
    -0.07
    ypse
    -0.06
    uhe
    -0.06
    POSITIVE LOGITS
    s
    0.10
    niest
    0.07
    ight
    0.06
     conscience
    0.06
     btn
    0.06
    sense
    0.06
    aden
    0.06
    R
    0.06
    shire
    0.06
     Stewart
    0.06
    Activations Density 0.002%

    No Known Activations