© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128411
    Prev
    Next
    INDEX
    Explanations

    numerical data related to health metrics and experimental results

    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
     another
    -0.07
    nech
    -0.06
    bucks
    -0.06
    oppel
    -0.06
    jian
    -0.06
    ãĥ¼ãĤº
    -0.06
    apter
    -0.06
    ÏĦοÏį
    -0.06
     itself
    -0.06
     serie
    -0.06
    POSITIVE LOGITS
     respectively
    0.29
     respective
    0.22
    åĪĨåĪ«
    0.21
     ÑģооÑĤвеÑĤ
    0.18
    respect
    0.15
     ê°ģê°ģ
    0.14
    ãģĿãĤĮ
    0.14
     sıras
    0.11
    ,res
    0.10
     вÑĸдповÑĸдно
    0.10
    Activations Density 0.108%

    No Known Activations