© 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. 5-LLAMASCOPE-RES-131K
    11. 125636
    Prev
    Next
    INDEX
    Explanations

    discussions about the challenges and significance of artistic expression and cultural institutions

    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
    cona
    -0.08
    coli
    -0.08
    ijn
    -0.07
    essler
    -0.07
    dater
    -0.07
    ën
    -0.07
    ARGET
    -0.07
    istrovstvÃŃ
    -0.07
    aminer
    -0.07
    .eql
    -0.07
    POSITIVE LOGITS
    itty
    0.06
    èĤ
    0.06
    cho
    0.06
     fault
    0.06
    YTE
    0.05
     Scho
    0.05
    rve
    0.05
    /Foundation
    0.05
    omal
    0.05
    @
    0.05
    Activations Density 0.093%

    No Known Activations