© 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. 125718
    Prev
    Next
    INDEX
    Explanations

    phrases indicating missed opportunities or exclusions

    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
    psilon
    -0.07
    ç¡
    -0.07
    ÛĮزÛĮ
    -0.07
    bai
    -0.07
    uo
    -0.06
    á»ģ
    -0.06
    æĸ¹éĿ¢
    -0.06
    ofs
    -0.06
    LEMENT
    -0.06
    aston
    -0.06
    POSITIVE LOGITS
    allback
    0.06
    ommen
    0.06
     Sabha
    0.06
    ungan
    0.06
     Cove
    0.06
    oman
    0.06
    ê´Ģ
    0.06
     äºĭ
    0.06
     val
    0.05
    /oct
    0.05
    Activations Density 0.002%

    No Known Activations