© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107101
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability and notifications

    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
    ycastle
    -0.07
    ÑĪин
    -0.07
    roat
    -0.06
    reetings
    -0.06
    oven
    -0.06
    å¹¹
    -0.06
    afone
    -0.06
    ÑĥÑĪки
    -0.06
    oot
    -0.06
    à¥įरब
    -0.06
    POSITIVE LOGITS
    Availability
    0.08
     availability
    0.08
    availability
    0.07
     Availability
    0.07
     again
    0.07
     matching
    0.07
     becomes
    0.06
    uss
    0.06
     dispon
    0.06
     available
    0.06
    Activations Density 0.003%

    No Known Activations