© 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. 17-LLAMASCOPE-RES-131K
    11. 83822
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direct quotations or statements

    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
    usz
    -0.08
     Marketable
    -0.07
    à¹Īà¸Ńà¸Ļ
    -0.07
    ony
    -0.07
    ylland
    -0.07
     dün
    -0.07
    ilm
    -0.07
     intr
    -0.06
    intr
    -0.06
    ̧
    -0.06
    POSITIVE LOGITS
     audiences
    0.07
    esel
    0.06
    ãģıãģł
    0.06
     audience
    0.06
    ytt
    0.06
    ween
    0.06
     اÙĦتÙĪ
    0.06
    formats
    0.06
    Ľi
    0.06
    osen
    0.06
    Activations Density 0.000%

    No Known Activations