© 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. 9-LLAMASCOPE-RES-131K
    11. 96732
    Prev
    Next
    INDEX
    Explanations

    elements related to workplace dynamics and relationships

    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
    iest
    -0.06
     spectrum
    -0.06
     Highlights
    -0.06
    ises
    -0.05
    512
    -0.05
    iri
    -0.05
    ories
    -0.05
    enburg
    -0.05
     visible
    -0.05
    rim
    -0.05
    POSITIVE LOGITS
    Ñĩим
    0.08
    brief
    0.08
    Brief
    0.08
     briefly
    0.07
    Äįel
    0.07
    گاÙĩÛĮ
    0.07
    ogui
    0.07
    ADX
    0.07
    ãĥĥãĥĦ
    0.07
    gua
    0.07
    Activations Density 0.350%

    No Known Activations