© 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. 5-LLAMASCOPE-RES-131K
    11. 126927
    Prev
    Next
    INDEX
    Explanations

    words indicating additional quantities or enhancements

    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
    irma
    -0.07
     maneuver
    -0.07
    arts
    -0.06
    esk
    -0.06
    wer
    -0.06
    acom
    -0.06
    ingle
    -0.06
    805
    -0.06
    PARATOR
    -0.06
    į
    -0.06
    POSITIVE LOGITS
    ctp
    0.07
    ajÄħ
    0.07
     Eck
    0.07
    :class
    0.06
    dojo
    0.06
    498
    0.06
    Ïģαν
    0.06
     Janeiro
    0.06
    οι
    0.06
    actionDate
    0.06
    Activations Density 0.006%

    No Known Activations