© 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. 74420
    Prev
    Next
    INDEX
    Explanations

    terms related to helpfulness and practicality

    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
    alles
    -0.07
     ngũ
    -0.07
     exhaust
    -0.06
    èī
    -0.06
    GenericType
    -0.06
    Priority
    -0.06
     aks
    -0.06
     tiener
    -0.06
    LEAN
    -0.06
    WE
    -0.06
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.08
     when
    0.08
    /help
    0.08
    ussy
    0.08
     regarding
    0.06
     WHEN
    0.06
    advert
    0.06
    udget
    0.06
     Kop
    0.06
     whenever
    0.06
    Activations Density 0.025%

    No Known Activations