© 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. 15-LLAMASCOPE-RES-131K
    11. 88590
    Prev
    Next
    INDEX
    Explanations

    words indicating appreciation or admiration for craftsmanship and design

    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
    ÑĢел
    -0.07
     miscar
    -0.07
    .Response
    -0.07
    asics
    -0.07
    åĬ
    -0.06
    ennon
    -0.06
    543
    -0.06
    883
    -0.06
     Ryder
    -0.06
    891
    -0.06
    POSITIVE LOGITS
     regs
    0.06
    ozÃŃ
    0.06
     builder
    0.06
     old
    0.06
     builders
    0.06
    etchup
    0.06
     tom
    0.06
     disp
    0.06
    lemn
    0.06
     hi
    0.06
    Activations Density 0.046%

    No Known Activations