© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128037
    Prev
    Next
    INDEX
    Explanations

    phrases indicating customer service and guidance

    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
    sandbox
    -0.07
    igo
    -0.07
    orz
    -0.07
    -animate
    -0.07
    atrice
    -0.06
    isÃŃ
    -0.06
    mÃŃt
    -0.06
     proven
    -0.06
    .VideoCapture
    -0.06
    (Unknown
    -0.06
    POSITIVE LOGITS
     process
    0.14
    process
    0.12
     processo
    0.10
    è¿ĩç¨ĭ
    0.10
     Process
    0.09
    Process
    0.09
    _process
    0.08
     пÑĢоÑĨеÑģÑģе
    0.08
     пÑĢоÑĨеÑģÑģ
    0.08
    -process
    0.08
    Activations Density 0.025%

    No Known Activations