© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27478
    Prev
    Next
    INDEX
    Explanations

    articles and indefinite pronouns in contexts denoting measurement or assessment

    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
    usa
    -0.08
    _Collections
    -0.07
    ContextHolder
    -0.07
    erce
    -0.06
    опаÑģ
    -0.06
     Aires
    -0.06
    StateManager
    -0.06
    .Xaml
    -0.06
    UDA
    -0.06
    oken
    -0.06
    POSITIVE LOGITS
     gut
    0.07
     ho
    0.07
    inh
    0.06
    aska
    0.06
    lage
    0.06
    BERT
    0.06
    çłĤ
    0.06
    avian
    0.06
    amba
    0.06
    elite
    0.06
    Activations Density 0.008%

    No Known Activations