© 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. 15-LLAMASCOPE-RES-131K
    11. 62380
    Prev
    Next
    INDEX
    Explanations

    references to celebrations and significant achievements

    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
    ury
    -0.06
     initState
    -0.06
    igu
    -0.06
    ovsky
    -0.06
    trak
    -0.06
    disposing
    -0.06
    -assets
    -0.06
    ÏģÏİν
    -0.06
    ilogy
    -0.06
    ickey
    -0.06
    POSITIVE LOGITS
    .linkedin
    0.06
     subs
    0.06
    одаÑĢ
    0.06
     connections
    0.06
    ÙĪÙĩ
    0.06
    716
    0.06
     connection
    0.06
     пÑĢиÑģ
    0.06
    oin
    0.06
     tet
    0.06
    Activations Density 0.029%

    No Known Activations