© 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. 17-LLAMASCOPE-RES-131K
    11. 74864
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or financial disclaimers and risk assessments

    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
    kie
    -0.07
    221
    -0.07
    247
    -0.06
    hs
    -0.06
    vie
    -0.06
    365
    -0.06
    riz
    -0.06
    ented
    -0.06
    777
    -0.06
    663
    -0.06
    POSITIVE LOGITS
    otos
    0.09
    ãģıãģł
    0.08
     nackte
    0.08
    اÙħÙĩ
    0.08
    ysi
    0.08
     evet
    0.08
     Demir
    0.08
    ,['
    0.07
    odyn
    0.07
    IVA
    0.07
    Activations Density 0.036%

    No Known Activations