© 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. 39797
    Prev
    Next
    INDEX
    Explanations

    references to relationships and associations, particularly regarding ties to specific groups or organizations

    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
    abei
    -0.08
    elyn
    -0.08
    _mt
    -0.07
    otor
    -0.07
    .scalablytyped
    -0.07
    zim
    -0.07
    ovel
    -0.07
    steen
    -0.07
    .nasa
    -0.07
    .Xaml
    -0.07
    POSITIVE LOGITS
    ages
    0.07
     connections
    0.06
     connection
    0.06
     severed
    0.06
    ABCDEFGHIJKLMNOP
    0.06
    aint
    0.06
     ties
    0.06
    uning
    0.06
    age
    0.06
     Cruc
    0.06
    Activations Density 0.012%

    No Known Activations