© 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. 59793
    Prev
    Next
    INDEX
    Explanations

    metrics related to performance and efficiency in business contexts

    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
    MAS
    -0.08
    æľ¬
    -0.07
    hog
    -0.07
    kud
    -0.07
    .datab
    -0.06
    idget
    -0.06
     Trou
    -0.06
    kas
    -0.06
    Trou
    -0.06
    atform
    -0.06
    POSITIVE LOGITS
     this
    0.15
    è¿Ļä¸Ģ
    0.13
    this
    0.12
     bunu
    0.11
     here
    0.11
     nÃły
    0.11
    æѤ
    0.10
    è¿Ļ个
    0.10
     regarding
    0.09
    >this
    0.09
    Activations Density 0.217%

    No Known Activations