© 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. 17-LLAMASCOPE-RES-131K
    11. 78902
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages related to financial or statistical information

    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
    yx
    -0.07
     اÙĦÙĨÙĪ
    -0.07
    /gui
    -0.06
    phon
    -0.06
    Latch
    -0.06
    ocre
    -0.06
    %%%%
    -0.06
    cest
    -0.06
    nger
    -0.06
    trag
    -0.06
    POSITIVE LOGITS
    udio
    0.06
    Ĺ
    0.06
    -placeholder
    0.06
     NaN
    0.06
    öh
    0.06
    woord
    0.06
    ÑĦи
    0.06
    owych
    0.06
    rica
    0.06
    ibble
    0.06
    Activations Density 0.013%

    No Known Activations