© 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. 16004
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to controversies and events in sports and other activities

    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
    ëĭ´
    -0.07
    ergus
    -0.06
    åĺĽ
    -0.06
    [].
    -0.06
     Pron
    -0.06
     Cove
    -0.06
    bulk
    -0.06
    HTTPRequest
    -0.06
    iste
    -0.06
    ConverterFactory
    -0.06
    POSITIVE LOGITS
     moo
    0.07
    undler
    0.06
    ayah
    0.06
    .bd
    0.06
    475
    0.06
     ones
    0.06
     yat
    0.06
     ÑĤого
    0.06
    erti
    0.06
    atables
    0.06
    Activations Density 0.022%

    No Known Activations