© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121464
    Prev
    Next
    INDEX
    Explanations

    elements related to software components and their states in a programming context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    eds
    -0.06
     g
    -0.06
    nea
    -0.06
    ect
    -0.06
    Configurer
    -0.06
     b
    -0.06
    ooks
    -0.06
    ":""
    -0.06
    à¥įतव
    -0.05
     Ao
    -0.05
    POSITIVE LOGITS
    uncate
    0.07
    ibur
    0.06
    ÐĴÑĸд
    0.06
    δÏģο
    0.06
    errat
    0.06
    anzeigen
    0.06
    ieux
    0.06
    nova
    0.06
    .cls
    0.06
    Å¡ak
    0.06
    Activations Density 0.001%

    No Known Activations