© 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. 17164
    Prev
    Next
    INDEX
    Explanations

    structural elements and indicators of construction or safety in contexts

    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
    tul
    -0.07
     hala
    -0.06
     dial
    -0.06
    é¡Į
    -0.06
     actionTypes
    -0.06
     Ramsey
    -0.06
     trục
    -0.06
     رض
    -0.06
    ContentView
    -0.06
    azor
    -0.06
    POSITIVE LOGITS
     kit
    0.07
     kits
    0.07
    žÃŃ
    0.06
     rain
    0.06
    ogui
    0.06
    ocus
    0.06
     Keystone
    0.06
    .ms
    0.06
     gutter
    0.06
    (åľŁ
    0.06
    Activations Density 0.000%

    No Known Activations