© 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. 77848
    Prev
    Next
    INDEX
    Explanations

    references to family size and relationships

    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
    atch
    -0.07
    ilib
    -0.07
    otal
    -0.07
    ibus
    -0.07
     znam
    -0.07
    бав
    -0.07
    ué
    -0.07
    oku
    -0.07
    ört
    -0.07
    elf
    -0.07
    POSITIVE LOGITS
    åĹ
    0.07
     sons
    0.06
    UNDLE
    0.06
     children
    0.06
     Chim
    0.06
     daughters
    0.06
    ResponseType
    0.06
    EventData
    0.05
    imestamp
    0.05
    evento
    0.05
    Activations Density 0.009%

    No Known Activations