© 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. 75870
    Prev
    Next
    INDEX
    Explanations

    references to professional roles and consulting activities

    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
    zure
    -0.07
    iyat
    -0.07
    зÑĭ
    -0.06
    culo
    -0.06
    ataka
    -0.06
    iyas
    -0.06
    empo
    -0.06
     MIS
    -0.06
    Painter
    -0.06
    ella
    -0.06
    POSITIVE LOGITS
     paid
    0.08
    paid
    0.07
    (None
    0.06
    utters
    0.06
    -scalable
    0.06
     receipt
    0.06
    -syntax
    0.06
     insp
    0.06
     royalty
    0.06
    .djangoproject
    0.06
    Activations Density 0.004%

    No Known Activations