© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88099
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize milestones and noteworthy events

    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
    incy
    -0.07
    иÑģлов
    -0.07
    òn
    -0.07
    rador
    -0.07
    éϵ
    -0.07
    essler
    -0.07
    ucas
    -0.07
     unborn
    -0.06
     karak
    -0.06
    _pickle
    -0.06
    POSITIVE LOGITS
     cul
    0.08
    cul
    0.07
    å¿Ļ
    0.06
     metast
    0.06
    867
    0.06
     highs
    0.06
    iest
    0.06
     events
    0.06
    èĽ
    0.06
     Aside
    0.06
    Activations Density 0.029%

    No Known Activations