© 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. 119699
    Prev
    Next
    INDEX
    Explanations

    references to tax-related topics and legal structures

    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
    onds
    -0.08
    emoc
    -0.07
    à¥ģà¤Ł
    -0.07
    asso
    -0.07
    aller
    -0.07
     temper
    -0.07
    ÑĥÑĢг
    -0.07
    çĦ¼
    -0.07
    ãĥķãĥ¬
    -0.07
    ãĥ³ãĤ¹
    -0.06
    POSITIVE LOGITS
     tax
    0.06
    796
    0.06
     scheme
    0.06
     BAT
    0.06
    omba
    0.06
     industry
    0.06
    ingen
    0.06
    ãĥ¼ãĥª
    0.06
    warts
    0.06
     Scheme
    0.05
    Activations Density 0.003%

    No Known Activations