Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43977
    Prev
    Next
    INDEX
    Explanations

    terms related to language structure and grammatical elements

    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
    istrovstvÃŃ
    -0.07
    eman
    -0.06
     than
    -0.06
     whose
    -0.06
     who
    -0.06
    idos
    -0.06
    ami
    -0.06
    еи
    -0.06
    atan
    -0.06
     voks
    -0.06
    POSITIVE LOGITS
     qu
    0.26
     que
    0.26
     ÑĩÑĤо
    0.14
     quil
    0.14
    Que
    0.14
    _que
    0.14
     Que
    0.14
     QUE
    0.13
    que
    0.13
     že
    0.13
    Activations Density 0.018%

    No Known Activations