© 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. 88032
    Prev
    Next
    INDEX
    Explanations

    computer code segments, particularly those related to image processing

    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
     nargs
    -0.07
    пи
    -0.07
    ird
    -0.07
    лан
    -0.06
    LANG
    -0.06
    agn
    -0.06
    iet
    -0.06
    eyed
    -0.06
     звеÑĢ
    -0.06
    ÐĿÐĨ
    -0.06
    POSITIVE LOGITS
    uator
    0.06
    sel
    0.06
    Õ¡
    0.06
    /***/
    0.06
    shader
    0.05
    .cells
    0.05
    xit
    0.05
    .gridColumn
    0.05
    ãĥ¥ãĥ¼
    0.05
    gd
    0.05
    Activations Density 0.032%

    No Known Activations