© 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. 85035
    Prev
    Next
    INDEX
    Explanations

    terms related to music festivals and legislative actions

    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
    ubber
    -0.07
     “
    -0.07
    ubbo
    -0.06
    ERG
    -0.06
    ứ
    -0.06
    -
    -0.06
     rather
    -0.06
    izzas
    -0.06
    hou
    -0.06
    åĢ
    -0.06
    POSITIVE LOGITS
     etc
    0.09
     ÑĤоÑīо
    0.07
    omaly
    0.07
    ,
    0.06
    ,proto
    0.06
     others
    0.06
    <quote
    0.06
    418
    0.06
    @nate
    0.06
    others
    0.06
    Activations Density 0.028%

    No Known Activations