© 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. 93610
    Prev
    Next
    INDEX
    Explanations

    various forms and expressions of confusion or uncertainty

    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
     circ
    -0.06
    actory
    -0.06
     alertController
    -0.06
     Allah
    -0.05
     Eig
    -0.05
     pressing
    -0.05
    rome
    -0.05
     mis
    -0.05
    502
    -0.05
    orm
    -0.05
    POSITIVE LOGITS
    tach
    0.07
     ож
    0.07
    ioc
    0.07
    ávÄĽ
    0.07
    à¸Ļาม
    0.07
    utch
    0.07
    ouse
    0.07
     hous
    0.06
    Ñģен
    0.06
    .':
    0.06
    Activations Density 0.008%

    No Known Activations