© 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. 130696
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to styles and formatting

    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
    åŀ
    -0.07
    locker
    -0.07
    á»Ļng
    -0.07
    .LookAndFeel
    -0.06
    ãģıãģł
    -0.06
     undermin
    -0.06
    eness
    -0.06
    á»ķ
    -0.06
    oute
    -0.06
    .Cursors
    -0.06
    POSITIVE LOGITS
    s
    0.08
    sted
    0.07
    nelly
    0.06
     Territory
    0.06
    ë°Ķ
    0.06
    kinson
    0.06
    idia
    0.06
    summ
    0.06
    Ĥ¹
    0.06
    lat
    0.06
    Activations Density 0.001%

    No Known Activations