© 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. 41056
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurements or experiments

    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
    ocuk
    -0.08
     edip
    -0.07
    .intent
    -0.07
    Ư
    -0.07
    ugin
    -0.07
    elsing
    -0.07
    .fi
    -0.07
    .NewLine
    -0.07
    &w
    -0.07
    \common
    -0.07
    POSITIVE LOGITS
    ãģĭãģª
    0.06
    /Foundation
    0.06
     mu
    0.06
     ke
    0.06
     .
    0.06
     none
    0.05
     sec
    0.05
     Exped
    0.05
     loosen
    0.05
     reform
    0.05
    Activations Density 0.245%

    No Known Activations