© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 85708
    Prev
    Next
    INDEX
    Explanations

    phrases related to service quality and credibility

    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
    uisine
    -0.06
    lain
    -0.06
    TTY
    -0.06
     Giles
    -0.06
    olen
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    æ·»
    -0.06
     ìķĦëĭĮ
    -0.06
    typ
    -0.06
    crete
    -0.06
    POSITIVE LOGITS
     anywhere
    0.10
     ever
    0.08
     Industry
    0.07
     industry
    0.07
    industry
    0.07
     jamais
    0.07
    Industry
    0.07
    æ¥Ń
    0.07
    ldr
    0.07
    vang
    0.06
    Activations Density 0.028%

    No Known Activations