© 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. 56883
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desire or intent

    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
    alem
    -0.07
    /kernel
    -0.07
    erk
    -0.07
    ัà¸ķà¸Ļ
    -0.07
    zk
    -0.07
    vla
    -0.07
    ÏĨο
    -0.07
     Susp
    -0.06
     inse
    -0.06
    ืà¹ī
    -0.06
    POSITIVE LOGITS
    оÑģÑĮ
    0.07
    833
    0.07
    ieder
    0.07
    lix
    0.06
    cloak
    0.06
    Setter
    0.06
    Builders
    0.06
    ondo
    0.06
     hearing
    0.06
    DSL
    0.06
    Activations Density 0.019%

    No Known Activations