© 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 EvalsExportsinterp-engineNEWAPI 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. 86410
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" in various contexts

    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
     Wyn
    -0.07
    lay
    -0.07
    ilo
    -0.07
     even
    -0.06
    libc
    -0.06
    utin
    -0.06
    uter
    -0.06
    elig
    -0.06
    å¥ı
    -0.06
    uet
    -0.06
    POSITIVE LOGITS
    ajo
    0.07
     Vance
    0.07
    лаз
    0.07
     conditions
    0.06
    &o
    0.06
    .cgi
    0.06
    dart
    0.06
    æŁ´
    0.06
    ë¹
    0.06
    ars
    0.06
    Activations Density 0.009%

    No Known Activations