© 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. 3769
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and assistance in providing information

    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
    imat
    -0.07
    éłĪ
    -0.06
    ноÑģ
    -0.06
    ÙİØŃ
    -0.06
     imper
    -0.06
     зан
    -0.06
    ÌĢ
    -0.06
    ноÑģи
    -0.06
    elson
    -0.06
     gains
    -0.06
    POSITIVE LOGITS
     convenience
    0.14
     convenient
    0.11
     Convenience
    0.11
     handy
    0.11
     ease
    0.10
     helpful
    0.10
     easy
    0.10
    ä¾Ľ
    0.09
     helps
    0.09
    æĸ¹
    0.09
    Activations Density 0.067%

    No Known Activations