© 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. 59594
    Prev
    Next
    INDEX
    Explanations

    phrases related to government policies and economic assistance

    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
    oyer
    -0.08
    کت
    -0.07
    δÏģο
    -0.07
    election
    -0.07
    inch
    -0.07
    алÑĭ
    -0.06
    antha
    -0.06
    ebek
    -0.06
     Fahr
    -0.06
    年度
    -0.06
    POSITIVE LOGITS
    ief
    0.06
     Hoover
    0.06
     fuck
    0.06
    1
    0.06
     TMPro
    0.06
    Fast
    0.06
    ieves
    0.06
     overnight
    0.06
     relief
    0.05
    out
    0.05
    Activations Density 0.002%

    No Known Activations