© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 86082
    Prev
    Next
    INDEX
    Explanations

    references to funding and awards related to scientific research and development

    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
     Ald
    -0.06
    incoming
    -0.06
    iceps
    -0.06
     walkthrough
    -0.06
    iseum
    -0.06
     premium
    -0.05
     Pur
    -0.05
    oud
    -0.05
     ad
    -0.05
    bast
    -0.05
    POSITIVE LOGITS
     è©
    0.07
    Research
    0.07
     Defense
    0.07
    usercontent
    0.07
     Small
    0.07
     Research
    0.07
     Sheridan
    0.07
    обов
    0.07
    .gov
    0.07
     Defence
    0.07
    Activations Density 0.004%

    No Known Activations