© 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 EvalsExportsinterp-engineNEWAPI 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. 41490
    Prev
    Next
    INDEX
    Explanations

    references to photography and visual representation

    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
     FIT
    -0.06
     Parks
    -0.05
    enton
    -0.05
    FIT
    -0.05
    È
    -0.05
    íĹĮ
    -0.05
     Cla
    -0.05
     Qu
    -0.05
    į¼
    -0.05
    lain
    -0.05
    POSITIVE LOGITS
    jang
    0.07
    رÙĪج
    0.07
    елем
    0.07
    /repos
    0.07
    ģn
    0.07
    .gridColumn
    0.06
    лÑİд
    0.06
    ARAM
    0.06
    erais
    0.06
    /boot
    0.06
    Activations Density 0.101%

    No Known Activations