© 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. 84474
    Prev
    Next
    INDEX
    Explanations

    intensifiers or adverbs that express degree, especially related to feelings or experiences

    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
    essel
    -0.06
    ãng
    -0.06
    ÑĢем
    -0.06
    Çİ
    -0.06
    reak
    -0.06
    áng
    -0.06
    ÅĤ
    -0.06
    anded
    -0.06
    atur
    -0.06
    ander
    -0.06
    POSITIVE LOGITS
     myself
    0.08
    engo
    0.07
    uja
    0.06
    outil
    0.06
    _NT
    0.06
    iaux
    0.06
     jsem
    0.06
     صاد
    0.06
    ÏĦία
    0.06
     PARTICULAR
    0.06
    Activations Density 0.028%

    No Known Activations