© 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. 16463
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming and animation effects

    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
     inventory
    -0.07
    -yyyy
    -0.06
    .SIG
    -0.06
    ehler
    -0.06
    loor
    -0.06
    Indented
    -0.06
    ä¸Ī
    -0.06
    owler
    -0.06
    лаб
    -0.06
    ιά
    -0.06
    POSITIVE LOGITS
     anim
    0.09
     animation
    0.07
    Interpolator
    0.07
    ÙĪÙĦÙĩ
    0.06
    anim
    0.06
    amt
    0.06
     Garner
    0.06
     easing
    0.06
    aksi
    0.06
    asl
    0.06
    Activations Density 0.012%

    No Known Activations