© 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. 80918
    Prev
    Next
    INDEX
    Explanations

    programming-related elements, particularly focusing on user interface or library components

    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
    365
    -0.08
    DNA
    -0.07
    dna
    -0.07
     Rochester
    -0.06
    quez
    -0.06
     Ao
    -0.06
     DNA
    -0.06
     Missouri
    -0.06
    antan
    -0.06
    墨
    -0.06
    POSITIVE LOGITS
    =wx
    0.09
     wx
    0.08
    .wx
    0.08
    çŃĭ
    0.07
    .serial
    0.07
     Ukr
    0.07
    ismet
    0.07
    indent
    0.06
     Miami
    0.06
    åĩ¡
    0.06
    Activations Density 0.003%

    No Known Activations