© 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. 56384
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligation or consequences of financial transactions

    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
     Canter
    -0.07
    ĥn
    -0.07
    ndef
    -0.07
    izio
    -0.07
    angkan
    -0.07
    oks
    -0.06
    ãĥĥãĥĦ
    -0.06
    iddy
    -0.06
    _DT
    -0.06
    åĨĨ
    -0.06
    POSITIVE LOGITS
     could
    0.21
     Could
    0.18
    Could
    0.16
    could
    0.16
     hätte
    0.15
     should
    0.12
     hät
    0.12
     могли
    0.12
     могла
    0.10
    ould
    0.10
    Activations Density 0.282%

    No Known Activations