© 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. 129012
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to changes and modifications in agreements or services

    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
    ÙħÙĬÙĦ
    -0.07
    Ñģок
    -0.06
    apa
    -0.06
    increments
    -0.06
    acking
    -0.06
    æļ
    -0.06
     Sil
    -0.06
     CrossRef
    -0.06
    ì°¬
    -0.06
    (Symbol
    -0.06
    POSITIVE LOGITS
     any
    0.08
    .crm
    0.07
     or
    0.07
    ovel
    0.06
    ä»»ä½ķ
    0.06
    cher
    0.06
    sburgh
    0.06
    ffen
    0.06
    ModelAttribute
    0.06
    tal
    0.06
    Activations Density 0.002%

    No Known Activations