© 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. 5-LLAMASCOPE-RES-131K
    11. 125830
    Prev
    Next
    INDEX
    Explanations

    references to professional roles and industries

    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
    chia
    -0.08
    anj
    -0.08
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.07
     Doyle
    -0.07
    overe
    -0.07
    ette
    -0.07
    bau
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    BOVE
    -0.07
    à¸ķะ
    -0.07
    POSITIVE LOGITS
     professional
    0.06
     ar
    0.06
     inferior
    0.06
     younger
    0.06
    -grade
    0.05
    professional
    0.05
     e
    0.05
    urr
    0.05
     (
    0.05
    anca
    0.05
    Activations Density 0.029%

    No Known Activations