© 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. 15-LLAMASCOPE-RES-131K
    11. 89431
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate responsibility and performance

    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
    биÑĤ
    -0.07
    ennen
    -0.07
    .override
    -0.07
    èªł
    -0.07
    ichi
    -0.07
    éric
    -0.07
    (æĹ¥
    -0.07
    неÑĤ
    -0.07
    ybrid
    -0.07
    ãĥ¼ãĥª
    -0.07
    POSITIVE LOGITS
     oneself
    0.07
    itag
    0.06
     such
    0.06
     yourself
    0.06
    werk
    0.06
     Panda
    0.06
     eng
    0.05
     name
    0.05
    rlen
    0.05
     Beau
    0.05
    Activations Density 0.040%

    No Known Activations