© 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. 128121
    Prev
    Next
    INDEX
    Explanations

    financial terms and conditions related to education

    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
    éri
    -0.06
     forget
    -0.06
     ì¡
    -0.06
     Grades
    -0.05
    æ±ł
    -0.05
    eka
    -0.05
     Hang
    -0.05
     pastor
    -0.05
    erti
    -0.05
    kas
    -0.05
    POSITIVE LOGITS
    tu
    0.09
    flater
    0.09
    TestFixture
    0.08
    expense
    0.08
     fees
    0.08
    resident
    0.08
    OptionsMenu
    0.07
    icana
    0.07
     Fees
    0.07
     tuition
    0.07
    Activations Density 0.004%

    No Known Activations