© 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. 119544
    Prev
    Next
    INDEX
    Explanations

    references to online shopping for products and services

    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
    Disposable
    -0.07
    earch
    -0.07
    perfil
    -0.06
    /aws
    -0.06
    kit
    -0.06
    Enumerable
    -0.06
     proc
    -0.06
     rfl
    -0.06
    ÑĩеÑģкое
    -0.06
    forma
    -0.06
    POSITIVE LOGITS
    rg
    0.08
    åIJ§
    0.07
    amedi
    0.07
    uthor
    0.06
     Sachs
    0.06
    uada
    0.06
    OGRAPH
    0.06
    質
    0.06
     indem
    0.06
     yourself
    0.06
    Activations Density 0.022%

    No Known Activations