© 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. 55142
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or repetition related to events or occurrences

    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
    vig
    -0.08
    istas
    -0.07
    xm
    -0.07
    arus
    -0.07
    nable
    -0.07
    IMPLEMENT
    -0.07
    ToUpper
    -0.06
    ç¢
    -0.06
    stvo
    -0.06
    oss
    -0.06
    POSITIVE LOGITS
     nor
    0.15
    nor
    0.09
     Nor
    0.08
     ani
    0.07
    Nor
    0.07
    ple
    0.06
    è¿Ļæł·çļĦ
    0.06
     illum
    0.06
     NOR
    0.06
     либо
    0.06
    Activations Density 0.005%

    No Known Activations