© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61920
    Prev
    Next
    INDEX
    Explanations

    phrases indicating excessive detail or minutiae in a discussion

    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
    IVA
    -0.06
     worthless
    -0.06
     amen
    -0.06
    oser
    -0.06
     Moon
    -0.06
    plib
    -0.06
    ions
    -0.06
    ousy
    -0.06
     zi
    -0.06
    anness
    -0.06
    POSITIVE LOGITS
     too
    0.09
    太
    0.09
     Too
    0.07
     太
    0.07
    ãģĻãģİ
    0.07
     TOO
    0.07
    too
    0.07
    лиÑĪком
    0.07
    774
    0.06
    Too
    0.06
    Activations Density 0.073%

    No Known Activations