© 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 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. 93767
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or expressions

    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
    .scalablytyped
    -0.09
    ÏĮ
    -0.07
     stol
    -0.07
    à¸ģà¸ķ
    -0.07
    ÄĽt
    -0.07
    buat
    -0.07
    ιά
    -0.07
     hers
    -0.07
    mine
    -0.07
    lest
    -0.07
    POSITIVE LOGITS
     blah
    0.06
    .LayoutStyle
    0.06
     [...]↵↵
    0.06
    htar
    0.06
     Lorem
    0.05
     Amph
    0.05
    âĢij
    0.05
     Vintage
    0.05
    PickerController
    0.05
    udes
    0.05
    Activations Density 0.007%

    No Known Activations