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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 103230
    Prev
    Next
    INDEX
    Explanations

    phrases related to cognitive challenges and misunderstandings in communication

    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
    Touches
    -0.07
    _Rect
    -0.07
    utsche
    -0.07
    ÌĨ
    -0.07
    touches
    -0.07
    iesel
    -0.07
    _catalog
    -0.07
    ium
    -0.07
    ilian
    -0.07
    opped
    -0.06
    POSITIVE LOGITS
    atest
    0.07
     ********************************************************************************
    0.06
     leading
    0.06
     urgently
    0.06
     embarrassing
    0.06
    _strdup
    0.06
     Sud
    0.06
     memor
    0.06
     sums
    0.06
     Milf
    0.06
    Activations Density 0.006%

    No Known Activations