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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30998
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confusion or misunderstandings

    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
    OAD
    -0.07
     sab
    -0.06
     Sab
    -0.06
    udic
    -0.06
    ÑĢеб
    -0.06
    WITHOUT
    -0.06
    $string
    -0.06
    IRD
    -0.06
    uuid
    -0.06
    uw
    -0.06
    POSITIVE LOGITS
     sondern
    0.21
     بÙĦÚ©Ùĩ
    0.18
     nor
    0.17
     Instead
    0.16
     sino
    0.16
    Instead
    0.15
     instead
    0.15
    nor
    0.14
    instead
    0.14
     anymore
    0.13
    Activations Density 0.111%

    No Known Activations