© 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. 125645
    Prev
    Next
    INDEX
    Explanations

    references to taxes and taxation-related themes

    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
    placer
    -0.07
     ãĤ¢ãĤ¤
    -0.07
     Homer
    -0.07
    ENTE
    -0.06
    ÅĻeba
    -0.06
    -minus
    -0.06
    rew
    -0.06
    ue
    -0.06
    redient
    -0.06
    lus
    -0.06
    POSITIVE LOGITS
    /MPL
    0.07
    inh
    0.07
    imeter
    0.06
    yc
    0.06
    ovel
    0.06
    omba
    0.06
     Wass
    0.06
    cth
    0.06
    xis
    0.06
     подав
    0.06
    Activations Density 0.017%

    No Known Activations